© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 33-TRANSCODER-HP
    7. 54565
    Prev
    Next
    INDEX
    Explanations

    fitness locations and activities

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    kick
    -0.28
    uet
    -0.27
    对çħ§æ£ĢæŁ¥
    -0.26
    adena
    -0.25
    nick
    -0.25
     INCIDENTAL
    -0.25
    odus
    -0.24
    otta
    -0.23
    exec
    -0.23
    ued
    -0.23
    POSITIVE LOGITS
    群ä½ĵ
    0.30
     laure
    0.29
     cor
    0.27
     Locker
    0.26
    æķ°æį®ä¸Ńå¿ĥ
    0.25
    zm
    0.25
     Laur
    0.25
    æ°´èµĦæºIJ
    0.25
    éĽĨåĽ¢
    0.25
    "group
    0.24
    Activations Density 0.031%

    No Known Activations