© 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. 21396
    Prev
    Next
    INDEX
    Explanations

    take in

    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
    lete
    -0.07
    enthe
    -0.06
    cht
    -0.06
    à¹Ħม
    -0.06
    ycz
    -0.06
    icularly
    -0.06
    chte
    -0.06
    ä¸įå°±
    -0.05
    ukul
    -0.05
    ners
    -0.05
    POSITIVE LOGITS
    çļĦä¸ĢåĪĩéĥ½
    0.06
    atron
    0.06
    ãģ«èĩ³
    0.05
     Miser
    0.05
    æĢ»åľ¨
    0.05
    uthor
    0.05
    лиз
    0.05
    åı
    0.05
    ropri
    0.05
    ä¹į
    0.05
    Activations Density 0.001%

    No Known Activations