© 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. 30539
    Prev
    Next
    INDEX
    Explanations

    use

    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
     salah
    -0.08
    мышл
    -0.07
    köp
    -0.07
    (Column
    -0.07
    _DA
    -0.07
    顯
    -0.07
    chos
    -0.07
    纳税
    -0.07
    -four
    -0.07
    的特点
    -0.07
    POSITIVE LOGITS
    :@"%@
    0.07
    agate
    0.07
    adiator
    0.07
    ült
    0.06
     Matthias
    0.06
     rigged
    0.06
     Wade
    0.06
     bigotry
    0.06
    trib
    0.06
    安全保障
    0.06
    Activations Density 0.001%

    No Known Activations