© 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. 41998
    Prev
    Next
    INDEX
    Explanations

    CK-MB, CK-MM, CK-BB, PDGF-BB

    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
    elope
    -0.06
    '
    -0.06
    _filepath
    -0.05
    .
    -0.05
    é£İéľľ
    -0.05
    ¯
    -0.05
    oute
    -0.05
    ãģĭãģĴ
    -0.05
    üm
    -0.05
    å¤ļä½Ļ
    -0.05
    POSITIVE LOGITS
    æĹ¥èµ·èĩ³
    0.09
    æĸĩæľ«
    0.08
    æĹ¥åĪ¶
    0.08
    stairs
    0.08
    æĹ¥èµ·
    0.08
    ocol
    0.08
    çijŀæĭī
    0.08
    ilere
    0.08
    ross
    0.08
    _OCCURRED
    0.08
    Activations Density 0.002%

    No Known Activations