© 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. 32-TRANSCODER-HP
    7. 42869
    Prev
    Next
    INDEX
    Explanations

    non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ascade
    -0.28
    åħ¸åŀĭ
    -0.27
    gps
    -0.26
    iot
    -0.26
    ieg
    -0.26
    arus
    -0.25
    feld
    -0.25
    IAN
    -0.25
     guts
    -0.24
    åħ±æĮ¯
    -0.24
    POSITIVE LOGITS
    深深
    0.27
     Lanka
    0.26
    æ·±æ·±åľ°
    0.26
     objectively
    0.26
     pos
    0.26
    =pos
    0.25
    è¿Ļ段
    0.25
    hek
    0.25
    lik
    0.24
    инÑĤеÑĢеÑģ
    0.24
    Activations Density 0.000%

    No Known Activations