© 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. 23959
    Prev
    Next
    INDEX
    Explanations

    symbol mu in equations

    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
    iée
    -0.07
    OrUpdate
    -0.07
    ometry
    -0.07
    er
    -0.07
    bite
    -0.06
    èĩªå·±çĭ¬çī¹çļĦ
    -0.06
    ãĤħãģĨ
    -0.06
    hips
    -0.06
    áŁĭ
    -0.06
    ividual
    -0.06
    POSITIVE LOGITS
    ìį¨
    0.11
    à¹Ħหรà¹Ī
    0.11
    licherweise
    0.10
    Ñģловно
    0.10
    ictured
    0.10
    Kostenloser
    0.10
    ikhail
    0.10
    ëłģ
    0.09
    innacle
    0.09
    Carthy
    0.09
    Activations Density 0.007%

    No Known Activations