© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 24799
    Prev
    Next
    INDEX
    Explanations

    know

    np_max-act · gemini-2.0-flash

    The neuron detects informative, attention-grabbing content words (proper names, technical terms, and other salient information-bearing tokens).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    落到
    -0.08
    <Button
    -0.08
    يدي
    -0.08
    -prof
    -0.07
    벳
    -0.07
    联动
    -0.07
     finden
    -0.07
     CSL
    -0.07
    得到
    -0.07
     '/')↵
    -0.07
    POSITIVE LOGITS
    แค
    0.09
    Common
    0.07
    �
    0.07
     removal
    0.07
     Honduras
    0.07
    それ
    0.07
    、↵↵
    0.07
     UIImage
    0.07
    >>();↵↵
    0.07
     Barr
    0.07
    Activations Density 3.789%

    No Known Activations