© 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. 12-TRANSCODER-HP
    7. 22793
    Prev
    Next
    INDEX
    Explanations

    technical documents, programming questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oined
    -0.31
    æ»ĭ润
    -0.28
     Mikhail
    -0.27
    atee
    -0.27
    ä½ı
    -0.26
    羨
    -0.26
    .isOn
    -0.24
    .cfg
    -0.24
    åĺ´
    -0.24
    erals
    -0.23
    POSITIVE LOGITS
    #line
    0.30
    otyping
    0.28
    åIJijä¸Ĭ
    0.27
     civil
    0.26
    ä¸ĭ鼨
    0.26
    æĭĨéĻ¤
    0.26
    éķ¿å®ī
    0.25
     creat
    0.25
    ä¸įæĸŃåľ°
    0.25
    Creat
    0.25
    Activations Density 0.000%

    No Known Activations