© 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. 40107
    Prev
    Next
    INDEX
    Explanations

    alpaca

    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
    å¹´èµ·
    -0.29
     experiment
    -0.28
    series
    -0.28
    ifes
    -0.27
    ursive
    -0.27
    ren
    -0.27
    onder
    -0.26
    次
    -0.26
    å¹´ä¸ŃåĽ½
    -0.25
     afterwards
    -0.25
    POSITIVE LOGITS
    p
    0.50
    pac
    0.42
    pak
    0.34
    çĵ¢
    0.31
    pw
    0.29
    pp
    0.28
    pa
    0.28
     clocks
    0.28
    oha
    0.28
    põ
    0.27
    Activations Density 0.050%

    No Known Activations