© 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. 21810
    Prev
    Next
    INDEX
    Explanations

    cough headache

    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
    orsi
    -0.07
    /trunk
    -0.07
    ä½łåį´
    -0.07
    ä½łåıĪ
    -0.06
     اÙĦÙĩر
    -0.06
     Consort
    -0.06
    è·»
    -0.06
     Ancora
    -0.06
    à¸Ħัà¸ļ
    -0.06
    Ùĩر
    -0.06
    POSITIVE LOGITS
    1
    0.06
    ç³»
    0.05
    声
    0.05
    è¡ĹçļĦ
    0.05
     ↵
    0.05
     cal
    0.05
    éģĵ
    0.05
     Rad
    0.05
    **
    0.04
     Per
    0.04
    Activations Density 0.002%

    No Known Activations