© 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. 111371
    Prev
    Next
    INDEX
    Explanations

    Dating profile descriptions

    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
     genau
    -0.07
    跟着
    -0.07
     아래
    -0.07
    也只是
    -0.06
     أغسط
    -0.06
    公開
    -0.06
     сервис
    -0.06
    卫
    -0.06
     ragaz
    -0.06
    登陆
    -0.06
    POSITIVE LOGITS
     gaps
    0.08
    箨
    0.07
     tiled
    0.07
    jsonwebtoken
    0.07
    㧬
    0.07
     gems
    0.07
    ="../../
    0.07
    comma
    0.07
    ocations
    0.07
    AGMA
    0.07
    Activations Density 0.075%

    No Known Activations