© 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. 17439
    Prev
    Next
    INDEX
    Explanations

    glass ionomer

    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
    abs
    -0.05
     Except
    -0.05
    ç»Ŀ
    -0.05
    åľ¨è¿ĻäºĽ
    -0.05
     ids
    -0.05
    æĸŃ
    -0.05
    çµķ
    -0.05
    åĿļ
    -0.05
    è¿ĻäºĽ
    -0.05
    æ¯Ķä¾ĭ
    -0.05
    POSITIVE LOGITS
    yak
    0.06
    جÙĬØ©
    0.06
    VR
    0.06
    -pack
    0.06
    avance
    0.06
    пÑĢавлÑı
    0.06
    ochond
    0.06
    chal
    0.06
    esi
    0.06
    ificador
    0.06
    Activations Density 0.228%

    No Known Activations