Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 87002
    Prev
    Next
    INDEX
    Explanations

    ITS

    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
    헿
    -0.07
    ベスト
    -0.07
     לנ
    -0.07
     Vin
    -0.07
     Weg
    -0.07
    rparr
    -0.07
     onload
    -0.07
     Gazette
    -0.07
    תכנון
    -0.06
    放假
    -0.06
    POSITIVE LOGITS
    (driver
    0.08
     able
    0.07
     $\
    0.07
     back
    0.07
     (`
    0.07
    multi
    0.07
     twitter
    0.07
     muscles
    0.07
     wol
    0.06
    .CR
    0.06
    Activations Density 0.002%

    No Known Activations