© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 89485
    Prev
    Next
    INDEX
    Explanations

    unpublished

    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
     stars
    -0.07
     在
    -0.07
    _permission
    -0.06
    简直
    -0.06
    姣
    -0.06
    心仪
    -0.06
    精湛
    -0.06
    分鐘
    -0.06
    将来
    -0.06
    cedes
    -0.06
    POSITIVE LOGITS
    なもの
    0.07
    _cols
    0.07
     organism
    0.07
    (avg
    0.07
     Dunn
    0.07
     discharge
    0.07
    _POP
    0.07
    (paths
    0.07
     ox
    0.07
    .bmp
    0.07
    Activations Density 0.000%

    No Known Activations