© 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. 142120
    Prev
    Next
    INDEX
    Explanations

    numbers and quantities

    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
     Knife
    -0.31
     patriotism
    -0.27
    ffffff
    -0.26
    Knife
    -0.26
    ç«Ļéķ¿
    -0.25
    è¶ħé«ĺ
    -0.25
     standing
    -0.24
     stret
    -0.24
     romance
    -0.23
     knife
    -0.23
    POSITIVE LOGITS
    åĪ¤å®ļ
    0.28
    otics
    0.28
    æ±°
    0.27
    eki
    0.27
    ains
    0.26
    稳妥
    0.25
    ä¸īçĤ¹
    0.25
    usch
    0.25
    rne
    0.25
    arna
    0.24
    Activations Density 1.508%

    No Known Activations