© 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. 22090
    Prev
    Next
    INDEX
    Explanations

    analytic, visual, and mathematical concepts

    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
    ä¸Ĭ身
    -0.06
    lined
    -0.06
    quine
    -0.06
    akes
    -0.06
     kolei
    -0.06
    зÑĭ
    -0.06
     salv
    -0.06
    éĩĮ头
    -0.06
    modified
    -0.06
    ÅĦcz
    -0.05
    POSITIVE LOGITS
    éĺ»
    0.05
    å¿ĥ
    0.05
    è®°
    0.05
     intuitive
    0.05
    itian
    0.05
    ickest
    0.05
    ledge
    0.05
    ×ķ×ij×Ķ
    0.05
    oub
    0.05
    à¸ģ
    0.05
    Activations Density 0.032%

    No Known Activations