© 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. 38779
    Prev
    Next
    INDEX
    Explanations

    descriptive modifiers

    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
    cen
    -0.09
    ĥ½
    -0.08
    大åĪ°
    -0.08
     enten
    -0.08
    çļĦéĤ£ä¸ªäºº
    -0.08
     entweder
    -0.08
    åĬłæĭ¿å¤§
    -0.08
    éĤ£éĩĮçļĦ
    -0.07
    agrams
    -0.07
    çĶļèĩ³æ¯Ķ
    -0.07
    POSITIVE LOGITS
    åĭ¿
    0.07
    że
    0.06
    èĩªå·²
    0.06
    åį³ä¸º
    0.06
    !.
    0.06
    éĶ¦æłĩ
    0.06
    ÑĬ
    0.06
    arre
    0.06
    u
    0.06
    -su
    0.06
    Activations Density 2.276%

    No Known Activations