© 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. 1931
    Prev
    Next
    INDEX
    Explanations

    Formula 1 racing

    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
    叙
    -0.07
    处分
    -0.07
    /qu
    -0.07
     Seamless
    -0.07
    $content
    -0.06
     affair
    -0.06
     Sao
    -0.06
    O
    -0.06
    orsi
    -0.06
    ocos
    -0.06
    POSITIVE LOGITS
    _pg
    0.07
     Publishing
    0.07
    宣传教育
    0.07
     Bray
    0.07
    的设计
    0.06
    _buy
    0.06
     dictated
    0.06
     Dirt
    0.06
     readability
    0.06
    晅
    0.06
    Activations Density 0.009%

    No Known Activations