© 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. 1102
    Prev
    Next
    INDEX
    Explanations

    `else if`

    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
    èĢĮä¸įæĺ¯
    -0.09
     tanpa
    -0.08
    anti
    -0.07
    èĢĮæĹł
    -0.07
     without
    -0.07
    èĢĮ没æľī
    -0.07
    asseur
    -0.07
     senza
    -0.07
    rather
    -0.07
    anced
    -0.07
    POSITIVE LOGITS
    elok
    0.08
    elos
    0.07
    çªģå¦Ĥåħ¶
    0.07
    ä¾ĥ
    0.07
    elmi
    0.07
    æķħ
    0.07
    elado
    0.07
    çĿIJ
    0.06
    elage
    0.06
    eding
    0.06
    Activations Density 0.046%

    No Known Activations