© 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. 15-RESID-POST-AA
    11. 24448
    Prev
    Next
    INDEX
    Explanations

    eh

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PACE
    -0.09
    ARC
    -0.07
     &
    -0.07
    (join
    -0.07
    inski
    -0.07
    audit
    -0.07
     Zodiac
    -0.07
    铸
    -0.07
    ADF
    -0.07
    uncio
    -0.07
    POSITIVE LOGITS
    依法追究
    0.08
     MonoBehaviour
    0.08
    .RecyclerView
    0.08
    ah
    0.08
     Reserved
    0.08
     utilizar
    0.07
    _deinit
    0.07
    服务器
    0.07
    ).[
    0.07
    是否
    0.07
    Activations Density 0.126%

    No Known Activations