© 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. 41255
    Prev
    Next
    INDEX
    Explanations

    news

    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
    主æĮģ人
    -0.28
     Ops
    -0.25
    oplan
    -0.25
    çĶŁäº§çļĦ
    -0.25
    iras
    -0.25
    ç
    -0.25
     thân
    -0.24
    åIJĮå¿Ĺ
    -0.24
    åľ°å¸¦
    -0.24
    ãĥĥãĥģ
    -0.24
    POSITIVE LOGITS
    è¯Ħ论
    0.27
    itz
    0.27
     quotes
    0.26
    éģķ
    0.26
    ĶåĽŀ
    0.25
    acles
    0.25
    æ¡Ħ
    0.25
     waiver
    0.24
    icia
    0.24
    ta
    0.24
    Activations Density 0.002%

    No Known Activations