© 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. 57235
    Prev
    Next
    INDEX
    Explanations

    unique, unlike, special

    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
    女巫
    -0.08
    à¸Ĭัà¹Īวà¸Ħราว
    -0.07
    amilan
    -0.07
     temporarily
    -0.07
    æģº
    -0.07
     nada
    -0.07
    PLICATION
    -0.07
    istar
    -0.07
    áŀ¶áŀĢ
    -0.07
    ned
    -0.07
    POSITIVE LOGITS
    ä¸įåĥı
    0.20
     unlike
    0.15
    Unlike
    0.13
     Unlike
    0.13
     unique
    0.13
    ä¸įå¦Ĥ
    0.12
    Unique
    0.12
     Unique
    0.12
    çļĦçĭ¬çī¹
    0.12
    çĭ¬çī¹
    0.12
    Activations Density 0.137%

    No Known Activations