© 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. 14754
    Prev
    Next
    INDEX
    Explanations

    ratios of overtone frequencies

    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
    _hook
    -0.08
    ichel
    -0.08
    äºĨ解ä¸Ģä¸ĭ
    -0.08
    неж
    -0.07
    strup
    -0.07
    antics
    -0.07
    landa
    -0.07
     cadr
    -0.07
    èıģ
    -0.07
    addle
    -0.07
    POSITIVE LOGITS
     ratios
    0.09
     Rat
    0.08
     ratio
    0.07
    ignan
    0.07
     relationships
    0.07
     gay
    0.06
     Ratio
    0.06
     numerical
    0.06
    ometr
    0.06
     numeric
    0.06
    Activations Density 0.001%

    No Known Activations