© 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. 107832
    Prev
    Next
    INDEX
    Explanations

    example

    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
    å®ķ
    -0.28
     mutating
    -0.27
     add
    -0.25
    éĥ½ä¸į
    -0.25
    #line
    -0.24
    åħ³éĹŃ
    -0.24
    èį·
    -0.24
    åĴĮå¹³
    -0.24
     Bình
    -0.24
    ADD
    -0.24
    POSITIVE LOGITS
     illustrating
    0.37
    ctest
    0.31
     Illustr
    0.31
    讽åĪº
    0.30
    é¢ĨæĤŁ
    0.30
     demonstrating
    0.30
    peek
    0.29
     Demon
    0.29
    ç«
    0.28
     demonstrates
    0.28
    Activations Density 45.376%

    No Known Activations