© 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. 39974
    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
    ede
    -0.27
    ypical
    -0.25
    èĥ±
    -0.24
    eden
    -0.24
    寵
    -0.24
    üss
    -0.24
    NH
    -0.24
    æµ·åºķ
    -0.24
    FW
    -0.24
    _part
    -0.24
    POSITIVE LOGITS
     TRAIN
    0.27
     Train
    0.26
     semif
    0.26
     Glo
    0.25
    殳
    0.24
    æµģéĩı
    0.24
     Scenes
    0.24
    sembl
    0.23
    .ini
    0.23
     egret
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.