© 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. 40392
    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
    ç«ł
    -0.28
    æ¹ĸåĮº
    -0.28
    èĥ½åĬĽåĴĮ
    -0.27
    èĤĩäºĭ
    -0.26
    åįı
    -0.25
     toned
    -0.25
    年度
    -0.25
    å¦Ĥä½ķçľĭå¾ħ
    -0.25
    ä¸Ģå°ı
    -0.25
     rendez
    -0.24
    POSITIVE LOGITS
    _rot
    0.27
    椹
    0.26
     hot
    0.25
     quickest
    0.25
    åģ¥åº·çļĦ
    0.25
    iped
    0.24
    _hot
    0.24
    çĤİçĥŃ
    0.24
    	pm
    0.23
    kul
    0.23
    Activations Density 56.514%

    No Known Activations

    This feature has no known activations.