© 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. 40173
    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
    [axis
    -0.27
    .instagram
    -0.25
    è¿ĺæĺ¯ä¼ļ
    -0.25
     Furious
    -0.24
     xúc
    -0.24
    .wx
    -0.23
    çıī
    -0.23
     Consort
    -0.23
    iments
    -0.23
    å¤ĸåªĴ
    -0.23
    POSITIVE LOGITS
    åħĪ
    0.26
    ç§ĺå¯Ĩ
    0.26
    arr
    0.26
    ITER
    0.26
    ren
    0.26
    æµģè¡Į
    0.26
    å®īåħ¨
    0.25
    æĽ°
    0.25
    åIJĮ
    0.25
    æľī个
    0.25
    Activations Density 70.827%

    No Known Activations

    This feature has no known activations.