© 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. 63716
    Prev
    Next
    INDEX
    Explanations

    winter storms, roof parts, echo's, laboratory experiments, winding rolls, restaurant's, Drama Fever, soluble tumour, CNC Art

    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
    åıĪä¸Ģ次
    -0.08
    ä¼ļè®®ä¸Ńå¿ĥ
    -0.07
    olla
    -0.07
    æľīåħ³è´Łè´£äºº
    -0.07
    quat
    -0.07
    çļĦä¸Ģ種
    -0.07
    æķĻèĤ²æĺ¯
    -0.07
    гÑĢаÑĦиÑı
    -0.06
    çļĦä¸ĢåIJį
    -0.06
    åĴĮèī¯å¥½çļĦ
    -0.06
    POSITIVE LOGITS
    -related
    0.09
    æģ¯æģ¯
    0.08
    onga
    0.07
    adden
    0.07
    âĢij
    0.07
    ores
    0.07
    -looking
    0.07
    ç»Ļ大家带æĿ¥
    0.07
    è¦ģç´ł
    0.07
    åħ·ä½ĵéĹ®é¢ĺ
    0.07
    Activations Density 0.943%

    No Known Activations