© 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. 21823
    Prev
    Next
    INDEX
    Explanations

    sequence from a character set with counts

    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
    سÙħ
    -0.07
    paralleled
    -0.07
    ðŁĻĤ
    -0.07
    èĢĮåĬ¨
    -0.07
    æīĢèĥ½åıĬ
    -0.07
    æij¸
    -0.06
    ingi
    -0.06
    à¹Į
    -0.06
    åĬ¨æĦŁ
    -0.06
    signin
    -0.06
    POSITIVE LOGITS
    èµĦ
    0.05
    ])))
    0.05
    ]):
    0.05
    aji
    0.05
    ÙĪÙĦÙĬ
    0.05
     hen
    0.05
    è¿ĶåĽŀ顶éĥ¨
    0.04
     slut
    0.04
     de
    0.04
    ä¼ĺåĮĸ
    0.04
    Activations Density 0.007%

    No Known Activations