© 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. 35-TRANSCODER-HP
    7. 40496
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    yı
    -0.26
     astore
    -0.25
    ISCO
    -0.25
    æĽ´å¤ļä¿¡æģ¯
    -0.24
    mü
    -0.24
     dicts
    -0.24
    å®ļåĪ¶
    -0.23
     autoc
    -0.23
     Wass
    -0.23
     Sas
    -0.23
    POSITIVE LOGITS
     Ñģмог
    0.27
    verted
    0.27
    åľº
    0.26
    æī§
    0.26
     fucking
    0.25
    åıĻ
    0.25
    è¿Ļ次
    0.25
    åıĤ
    0.24
    å¾ģ
    0.24
    è¿ĺæĺ¯
    0.24
    Activations Density 23.204%

    No Known Activations

    This feature has no known activations.