© 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. 21706
    Prev
    Next
    INDEX
    Explanations

    perturbation, linearized, relaxation, excitations, AC impedance

    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
     palm
    -0.06
    .font
    -0.06
    esper
    -0.06
    urat
    -0.06
    jew
    -0.06
    貫
    -0.06
     thi
    -0.06
    å¿ĥçĹĽ
    -0.06
    缺
    -0.05
    è§ģè¯ģ
    -0.05
    POSITIVE LOGITS
     autour
    0.09
     Inherits
    0.09
    ืà¸Ńà¸Ļ
    0.09
    kov
    0.09
    รà¸Ńà¸ļ
    0.08
     inherits
    0.08
    姨
    0.08
    lave
    0.08
    áŁĩ
    0.08
    uke
    0.08
    Activations Density 0.010%

    No Known Activations