© 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. 19-RESID-POST-AA
    11. 75893
    Prev
    Next
    INDEX
    Explanations

    conditioning

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "))))↵
    -0.07
    胴
    -0.07
    甚至连
    -0.07
    澂
    -0.07
     durée
    -0.07
    룅
    -0.07
     ethn
    -0.07
    晨报
    -0.07
    𫗴
    -0.07
    _Of
    -0.07
    POSITIVE LOGITS
    Kansas
    0.06
    Widget
    0.06
    America
    0.06
    _pressed
    0.06
     우리는
    0.06
    "",
    0.06
     options
    0.06
     버
    0.06
    }{$
    0.06
    stdafx
    0.06
    Activations Density 0.009%

    No Known Activations