© 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. 44896
    Prev
    Next
    INDEX
    Explanations

    fermions

    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
    ecker
    -0.08
    è²łãģij
    -0.07
    arness
    -0.07
    caster
    -0.07
    uable
    -0.07
    ë¥Ļ
    -0.07
    رÙĤ
    -0.07
    -issue
    -0.07
    aque
    -0.07
    cznie
    -0.06
    POSITIVE LOGITS
    /her
    0.08
    ington
    0.08
    ä»¬åľ¨
    0.08
    aceous
    0.07
    ity
    0.07
    инÑĥ
    0.07
    [Any
    0.07
    ä¸įæģ¯
    0.07
    licity
    0.07
    å¦ĤçĥŁ
    0.07
    Activations Density 0.005%

    No Known Activations