© 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. 64755
    Prev
    Next
    INDEX
    Explanations

    Lacking something

    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
    Negative Logits
    åĬªåĬĽ
    -0.25
     pedal
    -0.25
    rez
    -0.24
    chemy
    -0.24
    estre
    -0.24
    RTC
    -0.23
     pitched
    -0.23
    ÑĩÑĮ
    -0.23
    .exist
    -0.23
    ukt
    -0.23
    POSITIVE LOGITS
    odom
    0.27
    ILED
    0.26
    odon
    0.25
    çĻ
    0.24
    GetPosition
    0.24
    æĹ¥åĨħ
    0.24
    fk
    0.23
    驾驶è¯ģ
    0.23
    odu
    0.23
    é¾Ľ
    0.23
    Activations Density 6.863%

    No Known Activations