© 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. 13964
    Prev
    Next
    INDEX
    Explanations

    shingles openings

    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
     pat
    -0.07
    -
    -0.07
    “
    -0.06
    */
    -0.06
    ä¸ģ
    -0.06
    pro
    -0.06
     ...
    -0.06
    ini
    -0.06
    1
    -0.06
    -0.05
    POSITIVE LOGITS
    æĬ¥è®°èĢħ
    0.10
    getResponse
    0.09
    agno
    0.09
    akedown
    0.09
    以ä¸Ĭå°±æĺ¯åħ³äºİ
    0.09
    sWith
    0.08
    AGMENT
    0.08
    isman
    0.08
    Ñĥдо
    0.08
    ç½ijåıĭè¯Ħ论
    0.08
    Activations Density 0.375%

    No Known Activations