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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 48334
    Prev
    Next
    INDEX
    Explanations

    b

    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
     Adventures
    -0.08
     Fut
    -0.07
     ',',
    -0.07
     Plum
    -0.07
     rotten
    -0.07
     IMessage
    -0.07
    ,str
    -0.07
     ál
    -0.07
    腆
    -0.07
    晚间
    -0.07
    POSITIVE LOGITS
    fü
    0.07
    因此
    0.07
     deco
    0.06
     bast
    0.06
     ::
    0.06
    legen
    0.06
    舱
    0.06
     dashes
    0.06
    ((↵
    0.06
    (sock
    0.06
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.