© 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. 42253
    Prev
    Next
    INDEX
    Explanations

    filenames and code constructs

    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
    odata
    -0.07
    вики
    -0.07
    arts
    -0.07
    د
    -0.07
    arty
    -0.07
    ÑģÑı
    -0.07
    ä½Ĩæĺ¯æĪij
    -0.07
    ets
    -0.07
    åı¯æĺ¯æĪij
    -0.06
    æĪij以åIJİ
    -0.06
    POSITIVE LOGITS
    ãģ®ãģ¨ãģĵãĤį
    0.07
    ä»»çĶ±
    0.07
    меÑĢа
    0.07
    ä»»ä½ķæŶåĢĻ
    0.07
    äºĨçľ¼
    0.06
    å®ģåĮº
    0.06
    为äºĨ让
    0.06
    å®ŀå¤Ħ
    0.06
     '|'
    0.06
    æ¯Ľæ³½ä¸ľ
    0.06
    Activations Density 0.001%

    No Known Activations