© 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. 47388
    Prev
    Next
    INDEX
    Explanations

    Here is the explanation:punctuation, conjunctions, conjunctions, conjunctions

    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
    ä¸ī两
    -0.08
    мÑĭ
    -0.07
    Ñĩин
    -0.07
    éĿŀå¾Ĺ
    -0.07
    é¡»
    -0.06
    .Block
    -0.06
     Protest
    -0.06
    istici
    -0.06
     dig
    -0.06
    INY
    -0.06
    POSITIVE LOGITS
    å°¼å°Ķ
    0.08
    heur
    0.08
    aki
    0.07
    (&$
    0.07
    elle
    0.07
    arella
    0.07
    ัà¸Ķ
    0.07
    çĵ¤
    0.06
    ÑĢак
    0.06
    omaly
    0.06
    Activations Density 0.024%

    No Known Activations