© 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. 40323
    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
    åĴ¬
    -0.28
    gr
    -0.27
    æ©«
    -0.27
    erman
    -0.26
    op
    -0.26
    -gr
    -0.25
    ings
    -0.25
    kn
    -0.24
     Dub
    -0.24
    -good
    -0.24
    POSITIVE LOGITS
     sodom
    0.28
     Lesb
    0.26
     propriet
    0.26
    æľ¬åĽ½
    0.26
     intox
    0.25
    IOUS
    0.25
    è¡ĹåĮº
    0.25
    venta
    0.24
    \Redirect
    0.24
     fundament
    0.24
    Activations Density 70.645%

    No Known Activations

    This feature has no known activations.