© 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. 38867
    Prev
    Next
    INDEX
    Explanations

    "here" or "link" or "paste"

    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
    å¼ķçĶ³
    -0.08
    éģ
    -0.07
     spect
    -0.07
    arder
    -0.07
    mana
    -0.07
    è¾¹
    -0.07
    溢
    -0.07
    _MESSAGES
    -0.07
    绣çŃ¹å®īæİĴ
    -0.07
    èĬ¸
    -0.06
    POSITIVE LOGITS
    áty
    0.07
    вÑĭÑĪе
    0.07
    ORY
    0.07
    æīĢéĢī
    0.07
    ãĥĭãĥ¥
    0.07
    REN
    0.07
    ×IJ×Ļ×Ŀ
    0.07
    ammers
    0.07
    微信æī«çłģ
    0.07
    ighted
    0.07
    Activations Density 0.012%

    No Known Activations