© 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. 46730
    Prev
    Next
    INDEX
    Explanations

    finally, so, yet

    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
    али
    -0.07
    hir
    -0.07
    eling
    -0.07
    omm
    -0.07
    an
    -0.07
    ori
    -0.07
    paren
    -0.07
    a
    -0.06
    _SIG
    -0.06
    è¸
    -0.06
    POSITIVE LOGITS
    __()
    0.08
    ê²°
    0.07
    ztat
    0.07
    ToObject
    0.07
    ertz
    0.07
    ege
    0.07
    Å¡ta
    0.07
    让广大
    0.07
     suj
    0.07
    dag
    0.07
    Activations Density 0.001%

    No Known Activations