© 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. 21193
    Prev
    Next
    INDEX
    Explanations

    asking for help on Stack Overflow

    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
    azz
    -0.05
    Wow
    -0.05
    ç¦Ģ
    -0.05
     m
    -0.05
    åĵĩ
    -0.05
    羣
    -0.05
    åİħ
    -0.05
     vr
    -0.05
    way
    -0.05
    常温
    -0.05
    POSITIVE LOGITS
    strup
    0.06
    WISE
    0.06
    AREN
    0.06
    isure
    0.06
     Moms
    0.06
    åħ·ä½ĵéĹ®é¢ĺ
    0.06
    keyp
    0.06
    berge
    0.06
    erva
    0.06
    ponce
    0.06
    Activations Density 0.044%

    No Known Activations