© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 49642
    Prev
    Next
    INDEX
    Explanations

    ratings and boolean conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Âł
    -0.07
    acs
    -0.07
    ÑĶ
    -0.06
    acco
    -0.06
    upon
    -0.06
    amiento
    -0.06
    åĪĨæĺİ
    -0.06
    ÙĪت
    -0.06
    ä¸Ģå±Ĥ
    -0.06
    çݯ
    -0.06
    POSITIVE LOGITS
    رخ
    0.09
    ness
    0.09
    NESS
    0.08
    书è¯Ħ
    0.08
    aces
    0.07
    بخ
    0.07
    angen
    0.07
    ä»ģçĪ±
    0.07
    æ¸ħ纯
    0.07
    ennon
    0.07
    Activations Density 0.002%

    No Known Activations