© 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. 45536
    Prev
    Next
    INDEX
    Explanations

    book"

    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
    வà¯ĩ
    -0.08
     inol
    -0.08
    osso
    -0.08
    被çĶ³è¯·äºº
    -0.08
     éner
    -0.08
    Inverse
    -0.08
     Liebl
    -0.08
    .ops
    -0.08
    egi
    -0.08
     conséqu
    -0.08
    POSITIVE LOGITS
    itty
    0.08
    ↵
    0.07
     Lang
    0.06
     pend
    0.06
    cre
    0.06
     com
    0.06
     sub
    0.06
    uel
    0.06
    0.06
     pass
    0.06
    Activations Density 0.169%

    No Known Activations