© 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. 1154
    Prev
    Next
    INDEX
    Explanations

    actors' names

    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
    çĻ¾å®¶
    -0.07
    å®ķ
    -0.07
    onso
    -0.06
    æĿ¥ä¸ºå¤§å®¶
    -0.06
    å½ĵ家
    -0.06
    anda
    -0.06
    обÑĢа
    -0.06
    sty
    -0.06
    .fp
    -0.06
    æĹŃ
    -0.06
    POSITIVE LOGITS
    ló
    0.08
    æĺ¾å¾ĹæĽ´åĬł
    0.08
    ittle
    0.08
    èche
    0.07
     nothing
    0.07
    cott
    0.07
    .documentElement
    0.07
    annel
    0.07
    éĥ½æĺ¯æ¯Ķè¾ĥ
    0.07
    pedo
    0.07
    Activations Density 0.008%

    No Known Activations