© 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. 38657
    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
     traps
    -0.28
    æķ£
    -0.27
    èĤĮ
    -0.26
    	Py
    -0.26
     lòng
    -0.25
    éĻ¢
    -0.25
     sounded
    -0.25
    ÑģÑħод
    -0.25
    è¨Ģ
    -0.25
    妥åĸĦ
    -0.25
    POSITIVE LOGITS
    iger
    0.28
     Gazette
    0.28
    eced
    0.27
     Jahres
    0.27
    xEB
    0.25
    avigator
    0.25
    igor
    0.25
    ãĥIJãĥ¬
    0.25
    ocular
    0.25
    FormControl
    0.24
    Activations Density 0.055%

    No Known Activations

    This feature has no known activations.