© 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. 7680
    Prev
    Next
    INDEX
    Explanations

    suitability and substitute

    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
    reja
    -0.09
    ecil
    -0.08
    头çļĦ
    -0.08
    elon
    -0.08
    ož
    -0.08
    egen
    -0.08
    ä¾ĨçļĦ
    -0.08
    aldi
    -0.08
    antine
    -0.08
    emény
    -0.08
    POSITIVE LOGITS
    ably
    0.10
    æŀģäºĨ
    0.08
    à¸Ĺีà¹Īà¸Īะ
    0.08
    -looking
    0.08
    à¸ģารà¸ĵà¹Į
    0.07
    enge
    0.07
    ty
    0.07
    (sh
    0.07
    æĸ¼
    0.07
    ä¹ĭå¤Ħåľ¨äºİ
    0.07
    Activations Density 0.031%

    No Known Activations