© 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. 40084
    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
    éĿ¢ä¸Ĭ
    -0.27
     darn
    -0.25
     Gut
    -0.25
     lov
    -0.24
    |$
    -0.24
    -Series
    -0.24
    楮
    -0.24
    oser
    -0.23
     Tang
    -0.23
    -series
    -0.23
    POSITIVE LOGITS
     legacy
    0.26
    Legacy
    0.26
    legacy
    0.26
    NotAllowed
    0.25
    åīĶ
    0.25
    æ¤Ĵ
    0.24
    大佬
    0.24
     бÑĥд
    0.23
    åĨįçİ°
    0.23
    åīįè¾Ī
    0.23
    Activations Density 0.513%

    No Known Activations

    This feature has no known activations.