© 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. 38913
    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
    æĥħåĨµè¿Ľè¡Į
    -0.34
    жи
    -0.27
    ç½ij讯
    -0.27
    é³Į
    -0.26
    çī¹åĪ«å£°æĺİ
    -0.25
    (&:
    -0.25
    éĢĽ
    -0.25
     rotational
    -0.25
     realization
    -0.25
    edis
    -0.25
    POSITIVE LOGITS
    ycz
    0.27
    adera
    0.26
     Kurdistan
    0.25
    è¿Ļ次
    0.25
    Entropy
    0.24
     compañ
    0.23
    çľĭçľĭ
    0.23
    primer
    0.23
    ella
    0.23
     anyone
    0.22
    Activations Density 0.013%

    No Known Activations

    This feature has no known activations.