© 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. 88283
    Prev
    Next
    INDEX
    Explanations

    Parentheses and periods

    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
    ertino
    -0.25
     conv
    -0.25
     Hur
    -0.25
    -0.24
     exc
    -0.24
    çľ¼çķĮ
    -0.24
    andin
    -0.24
    _HP
    -0.24
    .dense
    -0.24
    emodel
    -0.23
    POSITIVE LOGITS
    yz
    0.26
    娱ä¹IJ
    0.25
    (md
    0.24
    igu
    0.24
    äºĮæľŁ
    0.24
    cmp
    0.24
    æĬ¥è®°èĢħ
    0.24
    è¯Ńæ³ķ
    0.23
    eah
    0.23
    yers
    0.23
    Activations Density 0.026%

    No Known Activations