© 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. 40399
    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
    æĪIJå°±
    -0.27
    ä¼´éļı
    -0.26
    Crow
    -0.26
    rush
    -0.25
     debut
    -0.25
     dev
    -0.25
    éĶ¦æłĩèµĽ
    -0.25
     poc
    -0.24
    åħļ
    -0.24
    tab
    -0.24
    POSITIVE LOGITS
    heimer
    0.28
    梧
    0.27
    ло
    0.27
     á»ķ
    0.26
     Uploaded
    0.25
     pais
    0.24
    åī¯åİ¿éķ¿
    0.24
    æ¡IJ
    0.24
     Tested
    0.24
    $req
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.