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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 24433
    Prev
    Next
    INDEX
    Explanations

    values

    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
     cận
    -0.07
    (cap
    -0.07
     sécurité
    -0.07
    .asp
    -0.07
    atical
    -0.07
    迕
    -0.07
    ajor
    -0.06
    てる
    -0.06
    ensaje
    -0.06
     IID
    -0.06
    POSITIVE LOGITS
    .getP
    0.07
    雪
    0.07
    (preg
    0.06
    🐖
    0.06
    _sk
    0.06
     kad
    0.06
    出手
    0.06
     Burning
    0.06
    Considering
    0.06
     observation
    0.06
    Activations Density 0.000%

    No Known Activations