© 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. 42522
    Prev
    Next
    INDEX
    Explanations

    technical content

    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
    ä¾Ŀæīĺ
    -0.27
     pursued
    -0.25
    :p
    -0.24
    éĺ¶
    -0.24
     mandated
    -0.24
    HA
    -0.24
    èµŀèµı
    -0.24
     ÐŁÐ¾Ñĩ
    -0.23
    _integral
    -0.23
     tack
    -0.23
    POSITIVE LOGITS
    annies
    0.28
    rosso
    0.28
    illian
    0.27
    骨
    0.26
     Gul
    0.25
    çĵ
    0.25
     trib
    0.25
    inya
    0.25
    é»ĺ
    0.24
    itchens
    0.24
    Activations Density 0.000%

    No Known Activations