© 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. 39514
    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
    ä»ĸ对
    -0.27
    UFFIX
    -0.26
    IONS
    -0.26
    æīĢ以ä»ĸ
    -0.26
     Engel
    -0.26
    ithe
    -0.26
     Kil
    -0.25
     His
    -0.25
    管
    -0.25
    His
    -0.25
    POSITIVE LOGITS
    ernaut
    0.30
     rosa
    0.28
    æ¸ij
    0.27
     лиÑĨ
    0.26
    âķ¯
    0.25
    ivated
    0.25
    ëŁī
    0.24
     Oprah
    0.23
    aminer
    0.23
    $$$$
    0.23
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.