© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 129648
    Prev
    Next
    INDEX
    Explanations

    Web code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    为代表
    -0.33
    memberof
    -0.32
    åħ¬åı¸åľ¨
    -0.31
    ä¸ŃåĽ½çļĦ
    -0.31
    CompanyId
    -0.30
     companyId
    -0.28
    对åħ¬åı¸
    -0.28
     belonging
    -0.28
    åħ¬åı¸çļĦ
    -0.28
     company
    -0.28
    POSITIVE LOGITS
    ussy
    0.29
    oux
    0.28
    éĤ®
    0.27
    ç¼Ĺ
    0.26
    ers
    0.26
    åİĭ
    0.26
     watchers
    0.25
    USD
    0.25
     !↵↵
    0.25
     blo
    0.24
    Activations Density 75.550%

    No Known Activations