© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7451
    Prev
    Next
    INDEX
    Explanations

    end of lines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    y
    -0.31
    in
    -0.30
    å·¥åľ°
    -0.28
     forc
    -0.28
    like
    -0.28
     intra
    -0.26
    Near
    -0.26
    æľ¬ç«Ļ
    -0.26
    intr
    -0.25
     sang
    -0.25
    POSITIVE LOGITS
    ofile
    0.28
     Jahres
    0.27
    phones
    0.26
    emento
    0.25
    (sf
    0.24
    -Methods
    0.24
    PHPUnit
    0.24
    æľīéĴ±
    0.24
    /movie
    0.24
    _Items
    0.23
    Activations Density 0.023%

    No Known Activations