© 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. 28300
    Prev
    Next
    INDEX
    Explanations

    .tex or

    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
    ]|[
    -0.07
    лез
    -0.07
     Harbor
    -0.07
    ;$
    -0.07
    oki
    -0.07
    erule
    -0.07
    wan
    -0.06
    ?',
    -0.06
    uzzi
    -0.06
    party
    -0.06
    POSITIVE LOGITS
    èķ¾
    0.08
    PTR
    0.07
    صاد
    0.07
    ê±´
    0.07
    à¹Ģà¸ĩ
    0.07
     ASM
    0.07
    adro
    0.07
    اج
    0.06
    odium
    0.06
    ั
    0.06
    Activations Density 0.006%

    No Known Activations