© 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. 142089
    Prev
    Next
    INDEX
    Explanations

    technical writing

    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
     sym
    -0.28
    åı¸
    -0.26
     sin
    -0.26
    ARA
    -0.26
    LETE
    -0.25
    holds
    -0.25
    çļĦæľĢåIJİä¸Ģ
    -0.25
    .setAuto
    -0.25
    ãĥ«ãĥī
    -0.24
     strongest
    -0.24
    POSITIVE LOGITS
    \brief
    0.28
    nov
    0.28
    åĪĨ离
    0.27
    uran
    0.27
    itel
    0.26
    è´¨éĩı管çIJĨ
    0.25
     separation
    0.25
    çıĻ
    0.25
    _io
    0.24
    [top
    0.24
    Activations Density 12.609%

    No Known Activations