© 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. 40785
    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
    AVIS
    -0.34
     Khá
    -0.30
    xFA
    -0.28
    CTYPE
    -0.27
     likeness
    -0.26
     choking
    -0.25
    èµĸ以
    -0.25
     kino
    -0.25
    çĻ½å¤©
    -0.25
     “âĢ¦
    -0.25
    POSITIVE LOGITS
     I
    0.33
     Ind
    0.33
    lin
    0.29
    ungen
    0.29
    us
    0.29
     Stud
    0.29
    ul
    0.28
    ind
    0.28
    com
    0.28
     Ir
    0.28
    Activations Density 20.226%

    No Known Activations

    This feature has no known activations.