© 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. 11177
    Prev
    Next
    INDEX
    Explanations

    degree, point, approach

    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
    认è¯ĨäºĨ
    -0.07
    æľĿ
    -0.07
    çĸ¼
    -0.06
     Erb
    -0.06
    离æĪij们
    -0.06
    pil
    -0.06
    åħ¨åĽ½åIJĦåľ°
    -0.06
    æĥħçļĦ
    -0.06
    bsite
    -0.06
    éķ¿éķ¿
    -0.06
    POSITIVE LOGITS
    æģķ
    0.08
     Neto
    0.08
    etus
    0.08
    anno
    0.08
    çĻ»å½ķæŁ¥çľĭ
    0.07
    大è§Ĥ
    0.07
    _MARGIN
    0.07
    Clr
    0.07
    ìĪł
    0.07
    toy
    0.07
    Activations Density 0.004%

    No Known Activations