© 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. 20072
    Prev
    Next
    INDEX
    Explanations

    expressions of thanks or sentiment

    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
    äºĨä¹Ī
    -0.06
     asm
    -0.05
    éħ¸
    -0.05
    ancio
    -0.05
    ì²ł
    -0.05
    oviÄĩ
    -0.05
    åıĤä¸İèĢħ
    -0.05
     jude
    -0.05
    äºĨåIJĹ
    -0.05
    isty
    -0.05
    POSITIVE LOGITS
    phem
    0.06
     rapidly
    0.06
    idata
    0.06
    对éĿ¢çļĦ
    0.06
    weite
    0.06
    XHR
    0.06
    å¦ĥ
    0.05
     desped
    0.05
    ston
    0.05
    ÑģÑĤÑĢе
    0.05
    Activations Density 0.007%

    No Known Activations