© 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. 42384
    Prev
    Next
    INDEX
    Explanations

    equivalents, values, produces, or relates

    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¸ĢæľĿ
    -0.08
    ä¸īéĥ¨æĽ²
    -0.08
    isses
    -0.07
    лиÑģÑĤ
    -0.07
    æݧ
    -0.07
    olz
    -0.07
    å¤©çľŁ
    -0.07
    æĤī
    -0.07
    ozy
    -0.07
    ä¸Ģèµ·
    -0.07
    POSITIVE LOGITS
     equival
    0.08
    æĪĸå°ij
    0.07
    转æį¢åĻ¨
    0.07
    æį¢ç®Ĺ
    0.07
    ãģĤãĤĮãģ°
    0.07
    avoir
    0.07
    drv
    0.07
    lerce
    0.07
    çļĦ空æ°Ķ
    0.07
    ouncil
    0.06
    Activations Density 0.004%

    No Known Activations