© 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. 20435
    Prev
    Next
    INDEX
    Explanations

    list of items

    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
    èŁ
    -0.05
     matched
    -0.05
     matches
    -0.05
    ä¸İæĻ®éĢļ
    -0.05
    del
    -0.05
    æĺ¯åIJ¦æŃ£å¸¸
    -0.05
    æľīéĥ¨åĪĨ
    -0.05
    èĨ¨
    -0.05
    ictions
    -0.05
     intersections
    -0.05
    POSITIVE LOGITS
    eros
    0.07
    ody
    0.06
    追éļı
    0.06
    ossi
    0.06
    ndef
    0.06
    ấ
    0.05
    ków
    0.05
    uters
    0.05
    éĻ¤æѤ
    0.05
    ony
    0.05
    Activations Density 0.002%

    No Known Activations