© 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. 63828
    Prev
    Next
    INDEX
    Explanations

    data availability/disclaimers

    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
     canvas
    -0.27
    ãĥ¼ãĥł
    -0.26
    .canvas
    -0.26
     Campus
    -0.26
     Venus
    -0.25
     rah
    -0.25
    ecessarily
    -0.24
    æĭī
    -0.24
    åħ¥åı£
    -0.24
    immers
    -0.23
    POSITIVE LOGITS
    å°ij
    0.32
     parted
    0.30
    theid
    0.28
    Euro
    0.25
    }}{{
    0.25
     divergence
    0.24
    isans
    0.24
    iska
    0.24
     REPRESENT
    0.23
    çİ°åĩº
    0.23
    Activations Density 1.171%

    No Known Activations