© 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. 38976
    Prev
    Next
    INDEX
    Explanations

    Autism spectrum disorder

    np_max-act-logits · gemini-2.0-flash
    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
     paras
    -0.28
     Mex
    -0.25
     Illustr
    -0.25
    /dc
    -0.25
    /ar
    -0.24
     ara
    -0.24
    инÑĤеÑĢ
    -0.24
    好å¤Ħ
    -0.24
    æ¢Ĺ
    -0.23
     Quiz
    -0.23
    POSITIVE LOGITS
    çѵ
    0.28
    itted
    0.27
     bipartisan
    0.26
    theless
    0.25
    ynomials
    0.25
    pe
    0.25
     bowl
    0.24
    çģ«è½¦
    0.24
     aired
    0.24
     quantify
    0.24
    Activations Density 0.047%

    No Known Activations