© 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. 129867
    Prev
    Next
    INDEX
    Explanations

    technical documentation/tutorials

    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
    EEP
    -0.30
    unker
    -0.28
     поÑı
    -0.27
    _listing
    -0.27
    RCT
    -0.27
    Others
    -0.26
    Ral
    -0.26
    Israel
    -0.26
    istol
    -0.26
     estates
    -0.25
    POSITIVE LOGITS
    RARY
    0.30
    ivre
    0.26
    ough
    0.26
    ãģ¡ãĤĩãģĨãģ©
    0.26
    ìĿ¸ì§Ģ
    0.25
    olds
    0.25
    .Sprintf
    0.25
    æ³½
    0.25
    æĪ·
    0.24
    ç§ijæĻ®
    0.24
    Activations Density 17.426%

    No Known Activations