© 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. 45473
    Prev
    Next
    INDEX
    Explanations

    the same as

    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
    è¯Ľ
    -0.08
     nevertheless
    -0.08
    zelfde
    -0.08
    izza
    -0.07
     nonetheless
    -0.07
    zing
    -0.07
    žas
    -0.07
    รัมยà¹Į
    -0.07
    åŃIJæĽ°
    -0.06
    ãģįãĤĮ
    -0.06
    POSITIVE LOGITS
     halnya
    0.11
     nhau
    0.10
    å¾Ģ常ä¸Ģæł·
    0.09
     those
    0.09
    ignment
    0.08
    åħ¶å®ĥ
    0.08
    éĤ£äºĽ
    0.07
    ä¸Ĭæĸĩ
    0.07
    åīįè¿°
    0.07
    оÑĢод
    0.07
    Activations Density 0.043%

    No Known Activations