© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 142409
    Prev
    Next
    INDEX
    Explanations

    URLs and code patterns

    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
     tháºŃp
    -0.30
    å¾Ĺ天
    -0.25
     znaj
    -0.24
    ÑĤоп
    -0.24
    èİĻ
    -0.24
    èĮ¨
    -0.24
    NIL
    -0.23
     Dec
    -0.23
     Ts
    -0.23
    yen
    -0.23
    POSITIVE LOGITS
    åı£è¢ĭ
    0.28
    çĬĦ
    0.25
    orts
    0.24
    æĺ¾
    0.24
    æĽ´åħ·
    0.24
     accom
    0.24
    jÃł
    0.24
    ingly
    0.24
    osis
    0.23
    NotFoundException
    0.23
    Activations Density 0.689%

    No Known Activations