© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16896
    Prev
    Next
    INDEX
    Explanations

    equivalent, equal, same, coincidence, interchangeable

    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
    å¦Ĥåħ¶
    -0.08
    çĶ±åħ¶
    -0.07
    ä¹ł
    -0.07
    lod
    -0.07
    å½ĵåħ¶
    -0.07
    veal
    -0.07
    ä¸įè¾¾
    -0.07
    plied
    -0.07
    yp
    -0.06
    íĮ©
    -0.06
    POSITIVE LOGITS
    äºĮèĢħ
    0.15
     equivalence
    0.13
    两èĢħ
    0.12
     coincidence
    0.11
    ivalence
    0.11
    åħ©èĢħ
    0.10
    çŃīåIJĮ
    0.10
     coincide
    0.10
    两èĢħçļĦ
    0.10
     Ñģов
    0.10
    Activations Density 0.055%

    No Known Activations