© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61760
    Prev
    Next
    INDEX
    Explanations

    section numbers or page references

    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
    zeb
    -0.08
    onato
    -0.08
     fronti
    -0.08
    StatusCode
    -0.08
    æIJŃçIJĨ
    -0.08
    ä½İèĩ³
    -0.08
    æĶ¿æ²»å±Ģ
    -0.08
    çĶ¸çĶ¸
    -0.08
    UCK
    -0.08
    PELL
    -0.08
    POSITIVE LOGITS
     probably
    0.09
     likely
    0.08
    æŁIJç§į
    0.08
     somehow
    0.07
    probably
    0.07
     presumably
    0.07
     Probably
    0.07
     somewhere
    0.07
    whatever
    0.07
     maybe
    0.07
    Activations Density 0.038%

    No Known Activations