© 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. 12934
    Prev
    Next
    INDEX
    Explanations

    mistakenly, coin, reverse, cancel, otherwise

    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
    ãĤĴ追åĬł
    -0.07
    esm
    -0.07
    Ñĩай
    -0.07
    fers
    -0.07
    ungi
    -0.07
    Legacy
    -0.07
    ients
    -0.06
     adicionais
    -0.06
    çļĦåıijçİ°
    -0.06
    elain
    -0.06
    POSITIVE LOGITS
    æĬµ
    0.08
    inverse
    0.08
    _cancel
    0.07
     inverse
    0.07
    åıį
    0.07
    åıįåIJij
    0.07
    (reverse
    0.07
    cancel
    0.07
    åıįèĢĮ
    0.07
    iele
    0.07
    Activations Density 0.001%

    No Known Activations