© 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. 22-TRANSCODER-HP
    7. 97864
    Prev
    Next
    INDEX
    Explanations

    studies/reports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ³Į
    -0.30
    usses
    -0.27
     facing
    -0.24
    æĸĩåĮĸ建设
    -0.24
    ç»Ħç»ĩå¼Ģå±ķ
    -0.24
    uild
    -0.24
    ONO
    -0.24
    áĥĸ
    -0.24
    plit
    -0.24
    èIJ½åIJİ
    -0.24
    POSITIVE LOGITS
    ringe
    0.28
     (£
    0.26
    çµķå°į
    0.25
    RATE
    0.25
    _major
    0.25
     nóng
    0.25
    Rated
    0.24
     prop
    0.24
     mù
    0.24
     absolutely
    0.24
    Activations Density 0.016%

    No Known Activations