© 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. 40382
    Prev
    Next
    INDEX
    Explanations

    scientific research

    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
     pare
    -0.47
     Pare
    -0.46
     Lore
    -0.42
    pare
    -0.39
     bere
    -0.37
     Bere
    -0.35
     dere
    -0.32
     Kare
    -0.31
     ré
    -0.30
     parece
    -0.29
    POSITIVE LOGITS
    à¸Ńà¸ļ
    0.32
    olls
    0.30
    è¿Ļä¸ī个
    0.29
    orb
    0.28
    ç»Ħç»ĩé¢Ĩ导
    0.27
    ookie
    0.26
    è¿Ļåĩłä¸ª
    0.26
    inherit
    0.25
    ç»Ħç»ĩçĶŁæ´»
    0.25
    exchange
    0.24
    Activations Density 0.221%

    No Known Activations