© 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. 1613
    Prev
    Next
    INDEX
    Explanations

    Behind, rearview mirrors, driving

    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
    就算
    -0.07
     incompet
    -0.07
    神州
    -0.07
    工作方案
    -0.06
    :"↵
    -0.06
     ию
    -0.06
    authors
    -0.06
    葚
    -0.06
     OCT
    -0.06
    潇
    -0.06
    POSITIVE LOGITS
    -terminal
    0.06
    -Semitic
    0.06
    饩
    0.06
    เล
    0.06
     glare
    0.06
     Pie
    0.06
     SAN
    0.06
     gm
    0.06
     Provider
    0.06
    .realm
    0.06
    Activations Density 0.048%

    No Known Activations