© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20615
    Prev
    Next
    INDEX
    Explanations

    recipient of information or service

    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
    rieve
    -0.05
     overlays
    -0.05
    å¯¹æľªæĿ¥
    -0.05
    åĹħ
    -0.05
    éĢ¸
    -0.05
     Ñĥгодно
    -0.05
     t
    -0.05
    è·¨è¶Ĭ
    -0.05
    icht
    -0.05
     analysis
    -0.05
    POSITIVE LOGITS
    gré
    0.07
     blat
    0.06
    ãĤµãĤ¤
    0.06
    jol
    0.06
    ibat
    0.06
    aldi
    0.06
    åİŁæĺ¯
    0.06
    æĴ¤
    0.06
    åİŁæĿ¥æĺ¯
    0.06
    original
    0.06
    Activations Density 0.018%

    No Known Activations