© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 39627
    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
    Solo
    -0.28
    éĤ£åıª
    -0.25
    (_,
    -0.24
    schlä
    -0.24
    åįĹéĿŀ
    -0.23
    (desc
    -0.23
    'E
    -0.23
    tings
    -0.23
    ç»Ĩç»Ĩ
    -0.22
    纳æĸ¯
    -0.22
    POSITIVE LOGITS
     w
    0.35
     r
    0.30
     h
    0.29
     j
    0.29
     fl
    0.28
     p
    0.27
     m
    0.27
     g
    0.26
     wake
    0.25
    ÃĤ
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.