© 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. 38664
    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
    åıĺ
    -0.27
    	Initialize
    -0.27
    å½±
    -0.26
    æħ¢æħ¢åľ°
    -0.26
    modele
    -0.24
    ofday
    -0.24
    ä¸īæľŁ
    -0.24
    æ¸IJ
    -0.24
    æħ¢æħ¢
    -0.24
    漫
    -0.23
    POSITIVE LOGITS
     ÑĢÑĥб
    0.30
    rib
    0.28
     междÑĥ
    0.26
    инг
    0.24
    ail
    0.24
    oval
    0.24
    SHARE
    0.23
    ibo
    0.23
     hosted
    0.23
    åĽŀåĽ½
    0.23
    Activations Density 0.047%

    No Known Activations

    This feature has no known activations.