© 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. 33195
    Prev
    Next
    INDEX
    Explanations

    letter combinations with subsequent punctuation/words

    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
    æĶ¯
    -0.08
    è·ĭ
    -0.07
     %(
    -0.07
     Shel
    -0.07
    اÙģت
    -0.07
    ĥ
    -0.07
    .fi
    -0.07
    飦
    -0.07
    æĿ¾
    -0.07
    ekon
    -0.07
    POSITIVE LOGITS
    Ī¬
    0.07
     overs
    0.07
    elo
    0.07
     haag
    0.06
    )test
    0.06
    ä½Ĩæĺ¯å¥¹
    0.06
    QÄIJ
    0.06
    ritic
    0.06
    iola
    0.06
     berbic
    0.06
    Activations Density 0.526%

    No Known Activations