© 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. 39820
    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
     master
    -0.26
     process
    -0.26
     swings
    -0.25
    æĹ¥æĬ¥ç¤¾
    -0.24
     caveat
    -0.24
     reunion
    -0.24
     tactic
    -0.24
     auto
    -0.23
     undercover
    -0.23
    é²Ĥ
    -0.23
    POSITIVE LOGITS
    lete
    0.26
    æ³Ħ
    0.26
    asive
    0.24
    æľīçļĦ
    0.24
     CÆ¡
    0.23
     Tech
    0.23
     Rect
    0.23
    anj
    0.23
     Fotos
    0.23
    èģĶ
    0.23
    Activations Density 2.661%

    No Known Activations

    This feature has no known activations.