© 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. 47549
    Prev
    Next
    INDEX
    Explanations

    else if

    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
    bove
    -0.08
    说åIJ§
    -0.08
    uenta
    -0.08
    uston
    -0.07
    çĮ¿
    -0.07
    kest
    -0.07
    ัà¸ĩ
    -0.07
    麦å½ĵ
    -0.07
    溪éķĩ
    -0.07
    enhagen
    -0.07
    POSITIVE LOGITS
    éĩĬ
    0.07
    çijļ
    0.06
    åĭ§
    0.06
    åıĪä¸į失
    0.06
     emp
    0.06
    å¤ļç§į
    0.06
    è¦
    0.06
    ä¸ĢåºĶ
    0.06
    ç»ĵæŀĦä¸İ
    0.06
    å½°
    0.06
    Activations Density 0.001%

    No Known Activations