© 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. 31090
    Prev
    Next
    INDEX
    Explanations

    derivative of

    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
    ms
    -0.07
    åľ°çº§
    -0.07
    åĪļ
    -0.07
    ini
    -0.07
    ium
    -0.07
    ingly
    -0.06
    iele
    -0.06
    å½ĵåħ¶
    -0.06
    交æĺĵæīĢ
    -0.06
     Target
    -0.06
    POSITIVE LOGITS
    .metamodel
    0.08
    weiler
    0.07
    jac
    0.07
    à¹Ģà¸Ħ
    0.07
    usaha
    0.07
    ÅŁte
    0.07
    ((&
    0.07
    eming
    0.07
    antie
    0.07
    çĸı
    0.06
    Activations Density 0.002%

    No Known Activations