© 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. 20123
    Prev
    Next
    INDEX
    Explanations

    can be

    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
    ä»»æĦı
    -0.09
     anytime
    -0.08
    éļıæĦı
    -0.07
     arbitrary
    -0.07
     anybody
    -0.06
     ability
    -0.06
     freely
    -0.06
    ä¸ŃçļĦä»»æĦı
    -0.06
     Arbitrary
    -0.06
    æĹ¶èµ·
    -0.06
    POSITIVE LOGITS
     modern
    0.06
    åŃĺåľ¨ä¸ĢäºĽ
    0.05
    lean
    0.05
     trades
    0.05
    åŃĺåľ¨æĦŁ
    0.05
     lega
    0.05
    以为çĦ¶
    0.05
     ÑģоÑĨи
    0.05
    áĥ¡
    0.05
    ç»·
    0.05
    Activations Density 0.052%

    No Known Activations