© 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. 17491
    Prev
    Next
    INDEX
    Explanations

    unless otherwise noted

    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
    áºŃy
    -0.07
    Sosial
    -0.07
    itamente
    -0.07
     seco
    -0.07
    alte
    -0.07
     doule
    -0.07
    =title
    -0.07
     newcom
    -0.07
     fevere
    -0.07
    itsu
    -0.07
    POSITIVE LOGITS
    ute
    0.05
    clin
    0.05
    cl
    0.05
    åĢĴæĺ¯
    0.05
    iker
    0.05
     permit
    0.04
    被
    0.04
     <
    0.04
     Sir
    0.04
    uto
    0.04
    Activations Density 0.002%

    No Known Activations