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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 19-RESID-POST-AA
    6. 59447
    Prev
    Next
    INDEX
    Explanations

    Top or bottom position

    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
     groupBox
    -0.08
     parents
    -0.07
    👄
    -0.07
    alphabet
    -0.07
     réuss
    -0.07
     �
    -0.07
    팡
    -0.06
    מסוגל
    -0.06
    <Token
    -0.06
    NotNil
    -0.06
    POSITIVE LOGITS
    冒
    0.08
    室
    0.07
     mínimo
    0.07
    .checkSelfPermission
    0.07
    前台
    0.07
    但是
    0.07
    集市
    0.07
     administrations
    0.07
    -water
    0.07
    赌场
    0.07
    Activations Density 0.061%

    No Known Activations