© 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. 7560
    Prev
    Next
    INDEX
    Explanations

    over all

    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
    åĪĨç±»åı·
    -0.08
    кои
    -0.08
    ekyll
    -0.08
    oros
    -0.07
    èī²åĪĹ
    -0.07
    çĿĢåĬĽçĤ¹
    -0.07
    óÅĤ
    -0.07
    jų
    -0.07
    å·¥ä½ľä½ľé£İ
    -0.07
    ofday
    -0.07
    POSITIVE LOGITS
    /about
    0.11
    /on
    0.11
    /out
    0.10
    /off
    0.10
    came
    0.10
    /by
    0.10
    /from
    0.09
    writes
    0.09
    heard
    0.08
    ials
    0.08
    Activations Density 0.058%

    No Known Activations