© 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. 21255
    Prev
    Next
    INDEX
    Explanations

    Math methods and properties

    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
    à¸Ĭีà¸ŀ
    -0.06
    еÑĪ
    -0.06
    ÑģполÑĮзÑĥ
    -0.06
    Å¡Äį
    -0.06
    ëįĺ
    -0.06
    stående
    -0.06
    sey
    -0.05
    esc
    -0.05
    ish
    -0.05
    zas
    -0.05
    POSITIVE LOGITS
    è¿ijå¹³
    0.07
    enko
    0.06
    mog
    0.06
    aux
    0.06
    äºĨæĪij们
    0.06
    izierung
    0.06
    вкÑĥ
    0.06
    iog
    0.06
    maks
    0.06
    ing
    0.06
    Activations Density 0.008%

    No Known Activations