© 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. 17201
    Prev
    Next
    INDEX
    Explanations

    confirmation or status

    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
    æĭŃçĽ®ä»¥å¾ħ
    -0.05
    è°ģ说
    -0.05
    -ready
    -0.05
     Ame
    -0.05
    dbl
    -0.05
     consent
    -0.05
    æľŁå¾ħ
    -0.05
    ruz
    -0.05
    Expected
    -0.05
     expected
    -0.05
    POSITIVE LOGITS
    archy
    0.06
    angkap
    0.06
    croft
    0.06
    滥
    0.06
    åľ¨å½ĵåľ°
    0.06
    庸
    0.06
     اÙĦÙħØ·
    0.06
    gger
    0.05
    pter
    0.05
    è¿ĻæĬĬ
    0.05
    Activations Density 0.002%

    No Known Activations