© 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. 4105
    Prev
    Next
    INDEX
    Explanations

    area / children / cause

    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
    èĭ¦å¹²
    -0.07
    á»ĩm
    -0.07
    ember
    -0.07
    åįģæĸ¹
    -0.07
    çĽħ
    -0.07
    ãĥ¯ãĥ¼ãĥ«ãĥī
    -0.07
    潺
    -0.07
    ikh
    -0.07
    sk
    -0.07
    жиÑĤ
    -0.07
    POSITIVE LOGITS
    åIJ«
    0.07
    åĮħæĭ¬äºĨ
    0.07
    èĪ
    0.07
    åĮħåIJ«äºĨ
    0.06
    etadata
    0.06
    大åĪ©
    0.06
    åľĴ
    0.06
     atomic
    0.06
    ense
    0.06
    FAULT
    0.06
    Activations Density 0.001%

    No Known Activations