© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21496
    Prev
    Next
    INDEX
    Explanations

    human glioma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mare
    -0.07
     lest
    -0.05
     susp
    -0.05
    worth
    -0.05
    enu
    -0.05
    roit
    -0.05
    et
    -0.05
    itari
    -0.05
     dit
    -0.05
    idet
    -0.05
    POSITIVE LOGITS
    èĪį
    0.06
    _human
    0.06
    æį¨
    0.05
    å¼ı设计
    0.05
    èĢĮå·²
    0.05
    human
    0.05
    à¹īาย
    0.05
    æĹłæģĻ
    0.05
    à¹Ģฮ
    0.05
     paš
    0.05
    Activations Density 0.046%

    No Known Activations