© 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. 48708
    Prev
    Next
    INDEX
    Explanations

    linear + technical terms

    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
    ëģĶ
    -0.09
    eenth
    -0.08
    аем
    -0.07
    ebin
    -0.07
    -fashioned
    -0.07
    tale
    -0.07
    ãĥ¼
    -0.07
    à¸ģารà¸ĵà¹Į
    -0.07
    داشت
    -0.06
    å¾Ĺèµ·
    -0.06
    POSITIVE LOGITS
    ly
    0.16
    mente
    0.15
    ities
    0.14
    idade
    0.13
    ität
    0.12
    idad
    0.11
    ization
    0.11
    ized
    0.11
    er
    0.10
    isation
    0.10
    Activations Density 0.032%

    No Known Activations