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. 129468
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Pendant
    -0.08
    NE
    -0.07
    ucked
    -0.07
    윌
    -0.07
     Neb
    -0.07
    igenous
    -0.07
    mpeg
    -0.07
    PWM
    -0.07
    闹
    -0.07
     Element
    -0.06
    POSITIVE LOGITS
    strtotime
    0.08
                                                           
    0.07
    வ
    0.07
    schlüsse
    0.07
    ()?>
    0.07
     ف
    0.07
    BaseUrl
    0.07
    _lab
    0.07
    -search
    0.06
     okreś
    0.06
    Activations Density 0.032%

    No Known Activations