© 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. 21461
    Prev
    Next
    INDEX
    Explanations

    using System.Collections.Generic

    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
    árt
    -0.08
     (!!
    -0.07
    صØŃ
    -0.07
    æĹłä¸į
    -0.07
    olate
    -0.06
    ืà¸Ń
    -0.06
    åıĮæĸ¹å½ĵäºĭ人
    -0.06
    fie
    -0.06
    esh
    -0.06
    iecz
    -0.06
    POSITIVE LOGITS
    åŃ
    0.09
    objs
    0.07
    -pos
    0.07
    èı²å°Ķå¾·
    0.07
     indef
    0.06
    åħ³æ³¨æĪij们
    0.06
    å¤ļçĤ¹
    0.06
    æµ·é»ĺ
    0.06
    NotAllowed
    0.06
     nurs
    0.06
    Activations Density 0.060%

    No Known Activations