© 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. 129135
    Prev
    Next
    INDEX
    Explanations

    living

    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
     stripslashes
    -0.07
     référence
    -0.07
    感官
    -0.07
    embourg
    -0.07
    ضيف
    -0.06
    glich
    -0.06
    --,
    -0.06
    溜
    -0.06
    VertexUvs
    -0.06
    eva
    -0.06
    POSITIVE LOGITS
     RuntimeError
    0.08
     MySQL
    0.07
    امت
    0.07
    敗
    0.07
    Keeping
    0.07
    CreateTime
    0.07
     Login
    0.07
     MQTT
    0.07
    假装
    0.07
    万元以上
    0.07
    Activations Density 0.020%

    No Known Activations