© 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. 39452
    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
     uÄŁra
    -0.27
    æ°´è´¨
    -0.27
     vår
    -0.27
    YES
    -0.26
    **
    -0.26
    .fl
    -0.26
    ials
    -0.26
    own
    -0.26
     our
    -0.25
    ene
    -0.25
    POSITIVE LOGITS
    ä¸įåħĭ
    0.28
    è¹
    0.27
    æĸ¹å¼ıè¿Ľè¡Į
    0.25
    该æ¡Ī
    0.25
    æķ´è½¦
    0.25
    -su
    0.25
    çĴĩ
    0.25
    доÑĢ
    0.24
    (components
    0.24
    dere
    0.24
    Activations Density 3.365%

    No Known Activations

    This feature has no known activations.