© 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. 17191
    Prev
    Next
    INDEX
    Explanations

    pricing structure and details

    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
    ÑĹ
    -0.05
    yp
    -0.05
    ambar
    -0.05
    orta
    -0.05
    o
    -0.05
    ecos
    -0.05
    ema
    -0.05
    人çļĦ
    -0.05
    æĴ
    -0.05
    yst
    -0.05
    POSITIVE LOGITS
    leftright
    0.08
    schild
    0.07
    sheets
    0.07
    LEASE
    0.07
    mÃ¼ÅŁ
    0.07
    dak
    0.07
    äºĨæĪij们
    0.07
    chenkt
    0.07
    äºĨä¸ī
    0.07
    chl
    0.06
    Activations Density 0.012%

    No Known Activations