© 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. 18854
    Prev
    Next
    INDEX
    Explanations

    removing or uninstalling

    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
    æĿ¥ä¹ĭ
    -0.06
    ')</
    -0.06
    orman
    -0.06
     )))
    -0.06
    esz
    -0.06
     téc
    -0.06
    engi
    -0.06
    isie
    -0.06
    Ñĩам
    -0.05
     Ones
    -0.05
    POSITIVE LOGITS
     Mad
    0.05
    åį°è±¡
    0.05
    hold
    0.05
     fest
    0.05
    å¹¿æ³ĽçļĦ
    0.05
    unas
    0.05
     retract
    0.05
    好åĥı
    0.05
    å·¦åı³
    0.05
    æ´»åĬ¨
    0.05
    Activations Density 0.022%

    No Known Activations