© 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. 38888
    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
     pity
    -0.28
    åĨµ
    -0.27
     differ
    -0.26
     Inherits
    -0.26
    æĭ¬
    -0.26
     næ
    -0.26
     belang
    -0.25
    äºĭçī©
    -0.25
     nét
    -0.25
     oportun
    -0.25
    POSITIVE LOGITS
    filer
    0.35
    äºĨä¸Ģåľº
    0.31
    ifix
    0.31
    atel
    0.31
    atively
    0.31
    iliated
    0.31
    ató
    0.28
    anken
    0.28
    ulously
    0.28
    cade
    0.27
    Activations Density 1.112%

    No Known Activations

    This feature has no known activations.