© 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. 22864
    Prev
    Next
    INDEX
    Explanations

    rooms and spaces

    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
    æīĵéĢļ
    -0.30
    驹
    -0.28
    æľºåħ³
    -0.28
    gram
    -0.25
    ç¥ģ
    -0.24
    orage
    -0.23
    æ©ŁéĹľ
    -0.23
    etting
    -0.23
    Ĥ¤
    -0.23
    ä¸Ģçľ¼
    -0.23
    POSITIVE LOGITS
    æı®
    0.27
     Magnet
    0.26
    byter
    0.26
    产ä¸ļåŁºåľ°
    0.26
    .compiler
    0.25
    å°Ĩ继ç»Ń
    0.25
    rax
    0.25
    avel
    0.24
     fert
    0.24
    zzo
    0.24
    Activations Density 0.001%

    No Known Activations