© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2163
    Prev
    Next
    INDEX
    Explanations

    numbers and chemical notation

    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¤ļåĬł
    -0.07
    ynom
    -0.07
    tap
    -0.07
    ukkan
    -0.07
    itech
    -0.07
    AccessType
    -0.06
    大èĩªçĦ¶çļĦ
    -0.06
    seau
    -0.06
    upas
    -0.06
    ä¸Ĭæī¬
    -0.06
    POSITIVE LOGITS
    áĢ°áĢ¸
    0.07
    ubern
    0.07
    åĩ«
    0.07
    hlen
    0.07
    Ĥ
    0.07
    Ú¯ÙĪÙĨ
    0.07
    æľĪçīĻ
    0.07
    -meta
    0.07
    venues
    0.07
    ×ķ×ķת
    0.06
    Activations Density 0.004%

    No Known Activations