© 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. 21518
    Prev
    Next
    INDEX
    Explanations

    ac-

    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
    åĩłå¹´çļĦ
    -0.06
    ossi
    -0.06
    ä¸įèĻļ
    -0.06
    ceg
    -0.06
    ÄĻg
    -0.06
    大å°Ĩ
    -0.06
    pike
    -0.06
    éĻ¥
    -0.06
    oraus
    -0.06
    ësh
    -0.06
    POSITIVE LOGITS
    çħŀ
    0.06
     how
    0.05
     remaining
    0.05
     surviving
    0.05
     endlessly
    0.05
    ä¸Ńç§ĭ
    0.05
     purely
    0.05
     k
    0.05
    éĢIJ
    0.05
    åĨ¥
    0.05
    Activations Density 0.004%

    No Known Activations