© 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. 17448
    Prev
    Next
    INDEX
    Explanations

    historical and technical descriptions

    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
    èĬĤ
    -0.05
    æį¢åı¥è¯Ŀ说
    -0.05
     Berm
    -0.05
    ä½ĵ
    -0.05
    ä¸ĵ项
    -0.05
     raz
    -0.05
    äu
    -0.05
    feld
    -0.05
     lob
    -0.04
    ä¹Łå°±æĺ¯è¯´
    -0.04
    POSITIVE LOGITS
     appunto
    0.08
    ç¡®æľī
    0.07
    確ãģĭãģ«
    0.07
     indeed
    0.07
    ç¡®å®ŀ
    0.06
    確實
    0.06
    ÙĪÙĦÛĮ
    0.06
    æĸī
    0.06
    ç¡®å®ŀæĺ¯
    0.06
    ugi
    0.06
    Activations Density 0.008%

    No Known Activations