© 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. 39656
    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
     B
    -0.27
    åIJĮè¡Į
    -0.26
     exclus
    -0.26
    è¸ıä¸Ĭ
    -0.25
     glamour
    -0.25
    ruc
    -0.24
    åĪĽå§ĭ人
    -0.24
    åĪĽå§ĭ
    -0.24
    å¹
    -0.24
    èIJ¥åĪ©
    -0.23
    POSITIVE LOGITS
    oxic
    0.27
     dụ
    0.26
    udios
    0.26
    oil
    0.25
    å¤ĸå¥Ĺ
    0.25
    Æ¡
    0.25
    Procedure
    0.24
    unity
    0.24
    çļĦé£Łçī©
    0.24
    ahoma
    0.24
    Activations Density 0.035%

    No Known Activations

    This feature has no known activations.