© 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. 63852
    Prev
    Next
    INDEX
    Explanations

    Possibility/Permission

    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
    赤
    -0.35
    ä¸Ĭä¸ĭ
    -0.28
    ROUGH
    -0.27
    oste
    -0.26
    prit
    -0.26
    warts
    -0.25
     Downing
    -0.24
    iband
    -0.23
    IFA
    -0.23
    hg
    -0.23
    POSITIVE LOGITS
     IRequest
    0.25
    æľĢåħĪ
    0.25
    QL
    0.24
    borne
    0.24
     permalink
    0.24
    åįĬ导
    0.23
    าà¸ģ
    0.23
     assoc
    0.23
     preferable
    0.23
     Guid
    0.23
    Activations Density 5.997%

    No Known Activations