© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42338
    Prev
    Next
    INDEX
    Explanations

    boolean values

    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
    çĦķ
    -0.07
    ®
    -0.07
     invitation
    -0.06
    è¾Ħ
    -0.06
     Cure
    -0.06
    pile
    -0.06
     todd
    -0.06
    æ°ijæŃĮ
    -0.06
    itung
    -0.06
    ä¸įæĭĺ
    -0.06
    POSITIVE LOGITS
    oader
    0.07
    èļ¤
    0.07
    ail
    0.07
    ourn
    0.07
     reason
    0.07
    åĨį继ç»Ń
    0.07
    ROADCAST
    0.07
    artal
    0.07
    çī¹éĩĮ
    0.07
    EventData
    0.07
    Activations Density 0.008%

    No Known Activations