© 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. 11-RESID-POST-AA
    11. 25347
    Prev
    Next
    INDEX
    Explanations

    Instructions and answer requests

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nga
    -0.07
    文创
    -0.07
    智能家居
    -0.07
     Diss
    -0.07
     아닌
    -0.06
    Own
    -0.06
     MyApp
    -0.06
    颛
    -0.06
    Meal
    -0.06
    matches
    -0.06
    POSITIVE LOGITS
    tracted
    0.07
    	CG
    0.07
     correcting
    0.07
    .object
    0.06
     treffen
    0.06
     getConnection
    0.06
     verbess
    0.06
    arrêt
    0.06
    pping
    0.06
    cessive
    0.06
    Activations Density 0.106%

    No Known Activations