© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14264
    Prev
    Next
    INDEX
    Explanations

    specific details

    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
    åħ¶æŀĹ
    -0.08
    stry
    -0.07
    ront
    -0.07
    ugo
    -0.07
    ÑģÑĤви
    -0.07
    tree
    -0.07
     parch
    -0.07
     Dude
    -0.07
    andle
    -0.07
    AndGet
    -0.07
    POSITIVE LOGITS
     specifics
    0.08
    _specific
    0.08
    åħ·ä½ĵ
    0.08
    olin
    0.07
    etid
    0.07
    åħ·ä½ĵæĿ¥è¯´
    0.07
    软åĮĸ
    0.07
     specific
    0.07
    specific
    0.07
    è´¡
    0.07
    Activations Density 0.002%

    No Known Activations