© 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. 46278
    Prev
    Next
    INDEX
    Explanations

    greater than or larger than

    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
    ánt
    -0.07
    æł·æł·
    -0.07
    æĺ¯å¤ļä¹Ī
    -0.07
    _orient
    -0.07
    trut
    -0.07
    unky
    -0.07
    usses
    -0.07
    antik
    -0.07
    agnol
    -0.07
     pang
    -0.06
    POSITIVE LOGITS
     threshold
    0.19
    è¶ħè¿ĩ
    0.19
     Threshold
    0.18
     thresholds
    0.18
    Threshold
    0.18
    _threshold
    0.18
    è¶ħè¿ĩäºĨ
    0.18
    threshold
    0.17
     exceeding
    0.17
    è¶³å¤Ł
    0.17
    Activations Density 0.342%

    No Known Activations