© 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. 97938
    Prev
    Next
    INDEX
    Explanations

    Code/database/filepaths

    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
    ilver
    -0.27
    åħ¬å¸ĥäºĨ
    -0.26
     persec
    -0.26
    æĻĴ
    -0.25
    ['
    -0.25
    пан
    -0.24
     today
    -0.24
    ä¸Ńåįİ人æ°ij
    -0.24
    __.__
    -0.24
    æľĭ
    -0.23
    POSITIVE LOGITS
    wner
    0.28
    大å¤ļæķ°äºº
    0.28
    /AP
    0.26
    顶
    0.26
    ä¸ĩ家
    0.25
    loat
    0.25
    autical
    0.24
    orary
    0.24
    ereço
    0.24
    nego
    0.24
    Activations Density 0.023%

    No Known Activations