© 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. 51348
    Prev
    Next
    INDEX
    Explanations

    claims for, to learn, how to, the electoral, the gradual

    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
    ä¸ľå±±
    -0.07
    avera
    -0.06
    alcon
    -0.06
    Newsletter
    -0.06
    /antlr
    -0.06
    inyin
    -0.06
    ×ķ×ĵ×Ķ
    -0.06
    æ·ĺ
    -0.06
     Bark
    -0.06
    abat
    -0.06
    POSITIVE LOGITS
     altrettanto
    0.10
     likewise
    0.09
     sebaliknya
    0.08
    éĢĨãģ«
    0.08
     pula
    0.08
     Sebaliknya
    0.07
     hingegen
    0.07
    .TryParse
    0.07
    åıįä¹ĭ
    0.07
     dagegen
    0.07
    Activations Density 0.915%

    No Known Activations