© 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. 64248
    Prev
    Next
    INDEX
    Explanations

    starting point or column

    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
    _inline
    -0.07
     underst
    -0.06
    upart
    -0.06
    çĶļèĢħ
    -0.06
    çݯæ¯Ķ
    -0.06
    快车
    -0.06
    είμε
    -0.06
    TB
    -0.06
    ewise
    -0.06
     hit
    -0.06
    POSITIVE LOGITS
    å§ĭ
    0.10
    åĩºåıij
    0.09
    æĮĩå®ļçļĦ
    0.08
    æĮĩå®ļ
    0.08
    OUTH
    0.08
    è®
    0.08
     ì¶ľë°ľ
    0.07
    åľ¨å¤ļ
    0.07
    -appointed
    0.07
    pecified
    0.07
    Activations Density 0.015%

    No Known Activations