© 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. 9835
    Prev
    Next
    INDEX
    Explanations

    modelLatv`, `float`, `narcotics`, `april`, `links`

    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
    ↵
    -0.07
    æĪĸèĢħ说
    -0.06
    æ·±æ·±åľ°
    -0.06
     (
    -0.06
    vez
    -0.06
    <|endoftext|>
    -0.06
     ('\
    -0.05
    صÙĬب
    -0.05
    ilenames
    -0.05
    æĢİæł·åģļ
    -0.05
    POSITIVE LOGITS
    çĦ¶å¤§
    0.08
     appunto
    0.08
     meds
    0.08
    chino
    0.07
    å¾Ĺ人
    0.07
    elden
    0.07
    igan
    0.07
    rey
    0.07
    æīįèĥ½ä¿Ŀè¯ģ
    0.07
     dicon
    0.07
    Activations Density 0.003%

    No Known Activations