© 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. 46759
    Prev
    Next
    INDEX
    Explanations

    actions and their results

    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
    Ùĭ
    -0.07
    å®ı
    -0.07
    atz
    -0.07
    Truthy
    -0.06
    åĴ¸
    -0.06
     Rez
    -0.06
    ç²Ĺ
    -0.06
     Medi
    -0.06
    令
    -0.06
    ä¸įåģľ
    -0.06
    POSITIVE LOGITS
    ÄIJT
    0.09
    esai
    0.09
     appunto
    0.09
    ä»ħæѤ
    0.08
    å½ĵä¹ĭ
    0.08
    å¿ĥäºĨ
    0.08
    åĪļåĪļ好
    0.07
    åħ°çī¹
    0.07
    usic
    0.07
     fetisch
    0.07
    Activations Density 0.041%

    No Known Activations