© 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. 15944
    Prev
    Next
    INDEX
    Explanations

    inversion and processor format

    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
    çŁ¥éŁ³
    -0.07
    edos
    -0.07
    çijŁ
    -0.07
    ืà¹Īà¸Ńย
    -0.07
    kho
    -0.07
     Hundred
    -0.07
    енÑĤов
    -0.07
    affiche
    -0.06
    conciliation
    -0.06
    å®ģ
    -0.06
    POSITIVE LOGITS
     technically
    0.08
    èĩªçĦ¶æĺ¯
    0.07
    à¸ķรà¹Į
    0.07
     truly
    0.07
    å½ĵçĦ¶æĺ¯
    0.07
     téc
    0.07
     perfectly
    0.07
     strictly
    0.07
    èĩªçĦ¶ä¹Ł
    0.07
    глÑĥ
    0.07
    Activations Density 0.086%

    No Known Activations