© 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. 21861
    Prev
    Next
    INDEX
    Explanations

    code object manipulation

    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
    éĿ¢æĹł
    -0.09
    óta
    -0.08
    æĹ¥è¡¨ç¤º
    -0.08
    istentes
    -0.08
    ÙĪرÙĩ
    -0.08
    wykle
    -0.07
     пÑĢоÑģÑĤÑĭм
    -0.07
    à¸İ
    -0.07
     Oeste
    -0.07
    antuan
    -0.07
    POSITIVE LOGITS
    0.06
    V
    0.06
    âĢ¦
    0.06
     V
    0.05
    åı¦
    0.05
    S
    0.05
     also
    0.05
    ï
    0.05
     a
    0.05
     met
    0.05
    Activations Density 0.004%

    No Known Activations