© 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. 39160
    Prev
    Next
    INDEX
    Explanations

    superconductivity, conductivity, magnetism

    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
    ings
    -0.06
    å¥Ĺ
    -0.06
    emen
    -0.06
    æľīæĥħ
    -0.06
    ä¹ĭ以
    -0.06
    rada
    -0.06
    åĴĮæĸ¹æ³ķ
    -0.06
    rum
    -0.06
    éĺ³æĺ¥
    -0.06
    ahmen
    -0.06
    POSITIVE LOGITS
    lesia
    0.08
    ores
    0.08
    তিà¦ķ
    0.08
    ucker
    0.08
    uchia
    0.08
    nikov
    0.08
    _ALIAS
    0.08
    ItemList
    0.08
    atsu
    0.07
    åħ¶ä¸ī
    0.07
    Activations Density 0.025%

    No Known Activations