© 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. 38696
    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
    Negative Logits
    ORMAT
    -0.29
    _backward
    -0.28
    诬
    -0.27
    ors
    -0.26
    kr
    -0.25
    trees
    -0.25
    ä¸ĢéĤĬ
    -0.25
     dig
    -0.24
    æŁĵ
    -0.24
     gre
    -0.24
    POSITIVE LOGITS
    asco
    0.31
    æ¯ıä½į
    0.28
    eya
    0.27
    æĺ¯ä¸Ģ项
    0.27
    edException
    0.26
    åľºæĻ¯
    0.26
    çĶµè·¯
    0.25
    åĪ°ä½į
    0.25
    è·³èĪŀ
    0.25
    åı¸
    0.25
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.