© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19136
    Prev
    Next
    INDEX
    Explanations

    mathematical fractions and integrals

    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
    owitz
    -0.06
    庸
    -0.06
    utz
    -0.06
     Nessun
    -0.06
    ê°ij
    -0.05
    здо
    -0.05
    rang
    -0.05
     Nossa
    -0.05
    ене
    -0.05
    agate
    -0.05
    POSITIVE LOGITS
    ä½ķåľ°
    0.06
     latter
    0.05
    اتÛĮ
    0.05
    orts
    0.05
    èĩªå·±
    0.05
    æĸĹ
    0.05
    çŃīä»·
    0.05
    milliseconds
    0.05
    éķ¿å¤§
    0.05
    wykle
    0.05
    Activations Density 0.008%

    No Known Activations