© 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. 130276
    Prev
    Next
    INDEX
    Explanations

    Informational text

    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
    eme
    -0.29
    atee
    -0.28
     entrev
    -0.27
    quirer
    -0.25
    emes
    -0.25
    帳
    -0.25
    -db
    -0.25
    ä¾ĭå¤ĸ
    -0.24
     Vib
    -0.24
    åIJ¯èĴĻ
    -0.24
    POSITIVE LOGITS
    å®ŀäºĭ
    0.26
     Tmax
    0.24
    ügen
    0.24
    hdl
    0.24
     GENERIC
    0.24
    æ³Ľ
    0.24
    ogne
    0.23
    ertype
    0.23
     ball
    0.23
    .DataType
    0.23
    Activations Density 5.007%

    No Known Activations