Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 41281
    Prev
    Next
    INDEX
    Explanations

    disappearance and change

    np_max-act · gemini-2.0-flash
    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
    HAV
    -0.07
    Median
    -0.07
     moisture
    -0.07
     wind
    -0.06
    doubleValue
    -0.06
    .ValidationError
    -0.06
     sand
    -0.06
    原油
    -0.06
    かなり
    -0.06
    .spawn
    -0.06
    POSITIVE LOGITS
     الرئيسية
    0.07
    <Tag
    0.07
    -display
    0.07
    :any
    0.07
    並同意
    0.07
    𝗚
    0.07
    -reader
    0.07
    (Application
    0.07
     '//
    0.07
    科创板
    0.07
    Activations Density 0.074%

    No Known Activations