© 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. 35-TRANSCODER-HP
    7. 40367
    Prev
    Next
    INDEX
    Explanations

    computer related text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     easy
    -0.27
    容æĺĵ
    -0.26
     relativ
    -0.25
    ertools
    -0.24
     Easy
    -0.24
     Ey
    -0.24
    _easy
    -0.24
    ç»Ħç»ĩå¼Ģå±ķ
    -0.24
     Yours
    -0.24
     tastes
    -0.24
    POSITIVE LOGITS
    abble
    0.34
    aab
    0.31
    以ä¸ĭæĺ¯
    0.29
    Ã¤ÃŁ
    0.28
    aroo
    0.28
    ogle
    0.28
    able
    0.28
    blr
    0.28
    AA
    0.27
    abbo
    0.27
    Activations Density 7.023%

    No Known Activations