© 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. 107145
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
    Meteor
    -0.27
    europ
    -0.25
    arbon
    -0.25
    iente
    -0.24
    æ°¸æģĴ
    -0.24
    ä¹ŁæĪIJ为
    -0.23
    others
    -0.23
     Harvey
    -0.23
    otle
    -0.23
     proced
    -0.23
    POSITIVE LOGITS
     leaked
    0.27
    æł¼
    0.26
    ,*
    0.25
    \Factory
    0.24
    æĹ¶è®¸
    0.24
     loose
    0.24
    ich
    0.24
    好å¥ĩå¿ĥ
    0.23
    wik
    0.23
     Proj
    0.23
    Activations Density 75.548%

    No Known Activations