© 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. 39129
    Prev
    Next
    INDEX
    Explanations

    musical notes or credit

    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
     sembl
    -0.08
    ä»¿ä½Ľæĺ¯
    -0.07
    Âł
    -0.06
    åĬ¨è¾Ħ
    -0.06
    è§Ĩ
    -0.06
    èĻ±
    -0.06
    inx
    -0.06
    ä¹ĸ
    -0.06
    æŃ¢
    -0.06
     Bal
    -0.06
    POSITIVE LOGITS
     egz
    0.08
     Burgess
    0.08
    tro
    0.08
    iszt
    0.07
    leid
    0.07
    ILLE
    0.07
    çĶ±åİŁåijĬ
    0.07
     '{$
    0.07
    大æŀ£
    0.07
    .bmp
    0.07
    Activations Density 0.040%

    No Known Activations