© 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. 40088
    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
    å²Ĥ
    -0.27
    åĨįå¤ļ
    -0.26
      ↵    ↵
    -0.25
    æĺ¯ä½ł
    -0.25
    DEST
    -0.24
    è¿ĺä¸įå¦Ĥ
    -0.24
    å¼Ħå¾Ĺ
    -0.24
    ution
    -0.24
    åı¯ä»¥æĽ´å¥½
    -0.23
    stag
    -0.23
    POSITIVE LOGITS
     resurrect
    0.26
     peripheral
    0.26
     accessor
    0.25
     restricting
    0.25
    åŃIJåħ¬åı¸
    0.24
    k
    0.23
     municipalities
    0.23
    æĺĤè´µ
    0.23
    çī¹å®ļ
    0.23
    ore
    0.22
    Activations Density 2.028%

    No Known Activations

    This feature has no known activations.