© 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. 21970
    Prev
    Next
    INDEX
    Explanations

    limits

    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
    Ø©
    -0.08
    ÏĤ
    -0.08
    ness
    -0.07
    aal
    -0.06
    æĿŁ
    -0.06
    ub
    -0.06
    elf
    -0.06
    ena
    -0.06
    evol
    -0.06
    etal
    -0.06
    POSITIVE LOGITS
    ä½Ĩä¸įéĻIJäºİ
    0.07
    éĩıçļĦ
    0.07
    ühl
    0.07
    æ®ĸ
    0.07
    axed
    0.06
    LOY
    0.06
    åĴĮä¸ĭ
    0.06
    phu
    0.06
    centaje
    0.06
    à¸ķราย
    0.06
    Activations Density 0.010%

    No Known Activations