© 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. 19442
    Prev
    Next
    INDEX
    Explanations

    deserved, adversaries, runner

    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
    éĦĻè§Ĩ
    -0.07
    aeda
    -0.07
    ëĵłì§Ģ
    -0.07
     discharged
    -0.07
    ording
    -0.06
     tzw
    -0.06
    aida
    -0.06
    pref
    -0.06
    iesel
    -0.06
    ä¾ĭå¦Ĥ
    -0.06
    POSITIVE LOGITS
     folks
    0.08
    没åķ¥
    0.08
     deserved
    0.08
     deserves
    0.08
    è¿ijäºĽå¹´
    0.07
    ä¸įå¤ļ说
    0.07
    aka
    0.07
    vias
    0.07
    odega
    0.07
    çľī
    0.07
    Activations Density 3.102%

    No Known Activations