© 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. 64037
    Prev
    Next
    INDEX
    Explanations

    Code, errors, and versions

    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
    {'
    -0.31
    åºľ
    -0.26
    ,eg
    -0.25
    _Parms
    -0.23
    itti
    -0.23
    =DB
    -0.23
    uck
    -0.23
    ặc
    -0.23
    _cid
    -0.23
     oz
    -0.23
    POSITIVE LOGITS
    oga
    0.29
    SHIP
    0.28
    past
    0.26
    oge
    0.25
     past
    0.25
    igkeit
    0.25
    oise
    0.24
    emain
    0.24
     thereof
    0.24
    ingles
    0.24
    Activations Density 27.986%

    No Known Activations