© 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. 40393
    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
    羣çIJĨ
    -0.28
    ä¸Ģé¡¿
    -0.27
    ä¹Łä¸įéĶĻ
    -0.26
    æ·º
    -0.26
    æµħ
    -0.26
     formation
    -0.26
     Formation
    -0.25
    åį´æ²¡æľī
    -0.25
    èĨ¨
    -0.25
    áŀī
    -0.25
    POSITIVE LOGITS
    å¾Ĵ
    0.29
    pite
    0.26
    ATE
    0.24
     conceive
    0.24
     ########################################################################
    0.24
    æŃ
    0.24
    pend
    0.24
    å¤ļ人
    0.24
     colspan
    0.23
     func
    0.23
    Activations Density 0.083%

    No Known Activations

    This feature has no known activations.