© 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. 21526
    Prev
    Next
    INDEX
    Explanations

    name spelling origin

    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
    åIJĪä½ľ
    -0.05
     prest
    -0.05
     analysed
    -0.05
    нали
    -0.05
    ç¡®å®ļ为
    -0.05
    oring
    -0.05
    åIJĪåIJĮ约å®ļ
    -0.05
    åģļ个
    -0.05
    qs
    -0.05
     critic
    -0.05
    POSITIVE LOGITS
    arão
    0.06
    ä¿ĿçķĻäºĨ
    0.06
    anci
    0.06
    æ±Ĥè´Ńä¿¡æģ¯
    0.06
    åįĬå±±
    0.06
    å±ħé«ĺ
    0.06
    ä¸Ńãģ§ãģĻ
    0.06
    bán
    0.06
     пÑĢиÑģÑĤа
    0.05
    terna
    0.05
    Activations Density 0.052%

    No Known Activations