© 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. 18129
    Prev
    Next
    INDEX
    Explanations

    special someone

    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
     unnamed
    -0.08
    éľĢè¦ģäºĨ解
    -0.07
    æľīåIJį
    -0.06
    ä½İ調
    -0.06
    ÙĪبات
    -0.06
    antan
    -0.06
    prot
    -0.06
    çŁ¥åIJį
    -0.06
    纫
    -0.06
    åľ°äºĨ解
    -0.06
    POSITIVE LOGITS
    符åIJĪ
    0.06
     screen
    0.05
    çģµ
    0.05
    V
    0.05
    å¥ijåIJĪ
    0.05
    лож
    0.05
    çļĦæĢĿæĥ³
    0.05
    ä¸Ĭä¹ĺ
    0.05
    åįĥ
    0.05
     Field
    0.04
    Activations Density 0.020%

    No Known Activations