© 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. 27-TRANSCODER-HP
    7. 9219
    Prev
    Next
    INDEX
    Explanations

    code/programming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Conditioning
    -0.25
    -condition
    -0.24
     RETURNS
    -0.24
    ذا
    -0.24
    aire
    -0.24
    IFS
    -0.23
    %);↵
    -0.23
    åįģå¹´
    -0.23
    ifs
    -0.23
    ç²¾
    -0.23
    POSITIVE LOGITS
     steam
    0.25
     favor
    0.25
     swallowed
    0.25
     terr
    0.24
     inc
    0.24
     Contest
    0.24
     tram
    0.24
     fav
    0.24
    éĺĻ
    0.24
    strom
    0.23
    Activations Density 0.002%

    No Known Activations