© 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. 21541
    Prev
    Next
    INDEX
    Explanations

    to help

    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
    宪
    -0.06
    bili
    -0.06
    éĻ·
    -0.06
     geng
    -0.05
    边走
    -0.05
    avig
    -0.05
    ÙĪÙĦÛĮ
    -0.05
    éĥ½è¯´
    -0.05
    @mail
    -0.05
    iÃŁ
    -0.05
    POSITIVE LOGITS
    icast
    0.06
    æĺ¾èijĹ
    0.05
    oned
    0.05
    vel
    0.05
     Significant
    0.05
    è¿Ļæľ¬
    0.05
    ound
    0.05
    significant
    0.05
    夫åIJĽ
    0.05
    onen
    0.05
    Activations Density 0.001%

    No Known Activations