© 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. 23364
    Prev
    Next
    INDEX
    Explanations

    static (programming)

    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
     fís
    -0.07
    .listFiles
    -0.07
     toxin
    -0.07
     shard
    -0.07
     commencement
    -0.07
     Sham
    -0.06
     cerca
    -0.06
     privé
    -0.06
    列车
    -0.06
    setMessage
    -0.06
    POSITIVE LOGITS
    TEMPLATE
    0.07
    见效
    0.07
    ROUT
    0.07
    Relations
    0.07
    APER
    0.07
    瘿
    0.06
     WHITE
    0.06
     territories
    0.06
     Parr
    0.06
    анд
    0.06
    Activations Density 0.045%

    No Known Activations