© 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. 57841
    Prev
    Next
    INDEX
    Explanations

    continuously increasing variable

    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
    ippet
    -0.07
     Automat
    -0.07
    åĻª
    -0.07
    身ä¸Ĭä¸ĭ
    -0.07
    uga
    -0.07
    istring
    -0.07
    æ¯ıéļĶ
    -0.07
     ngẫu
    -0.06
    liness
    -0.06
    strup
    -0.06
    POSITIVE LOGITS
     exceed
    0.12
     negative
    0.12
    åľ¨æŁIJäºĽ
    0.11
    è·Įçł´
    0.11
    è¶ħåĩºäºĨ
    0.11
     exceeding
    0.11
    negative
    0.11
     inverted
    0.11
    -negative
    0.10
     exceeds
    0.10
    Activations Density 0.039%

    No Known Activations