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. 2310
    Prev
    Next
    INDEX
    Explanations

    results

    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
    évén
    -0.07
     every
    -0.07
     HA
    -0.07
    行った
    -0.06
     tendency
    -0.06
    𬭯
    -0.06
    뇽
    -0.06
    زو
    -0.06
     stray
    -0.06
    údo
    -0.06
    POSITIVE LOGITS
    ими
    0.07
    不该
    0.07
    _Admin
    0.07
    declaring
    0.07
    吊顶
    0.07
    _SCAN
    0.07
    Unsafe
    0.07
    urning
    0.07
    >/<
    0.06
     대부
    0.06
    Activations Density 0.161%

    No Known Activations