© 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. 3543
    Prev
    Next
    INDEX
    Explanations

    allegations and related claims

    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
    èĢĮæĺĵ
    -0.08
    psilon
    -0.08
    fachen
    -0.08
    ä¼ijæĹ¥
    -0.07
    tig
    -0.07
    trl
    -0.07
    roadcast
    -0.07
    osamente
    -0.07
    æĢİ麼辦
    -0.06
    æĪijåIJ§
    -0.06
    POSITIVE LOGITS
     scrim
    0.06
    åĪ®
    0.06
     aforementioned
    0.06
    ütte
    0.06
    ä¹IJä¹İ
    0.06
    ócz
    0.06
    æ¥ł
    0.06
    rote
    0.06
    çļĦåľºæĻ¯
    0.06
    engang
    0.06
    Activations Density 0.052%

    No Known Activations