© 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. 49501
    Prev
    Next
    INDEX
    Explanations

    left to right

    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
    Editable
    -0.08
     anytime
    -0.07
    roid
    -0.07
    ritti
    -0.07
    ÐŃÐļ
    -0.07
     deps
    -0.07
    çĭ¬
    -0.07
     Ride
    -0.07
    äºĭåħĪ
    -0.07
     ÄijÆ°Æ¡ng
    -0.07
    POSITIVE LOGITS
    andes
    0.07
    unga
    0.07
    à¸ļา
    0.07
    å°±è§ģ
    0.07
    isky
    0.07
    acz
    0.07
    çĽ¸ä¿¡ä½ł
    0.06
    çļĭ
    0.06
    aku
    0.06
    å£
    0.06
    Activations Density 0.001%

    No Known Activations