© 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. 16370
    Prev
    Next
    INDEX
    Explanations

    infants and animals

    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
    idi
    -0.08
     ÙĤب
    -0.08
    æĮ«
    -0.08
     Gradu
    -0.08
    columnName
    -0.07
    ðŁĺī
    -0.07
    ÑĩÑĮÑİ
    -0.07
    æ¯ķä¸ļäºĨ
    -0.07
    veille
    -0.07
    èĶĶ
    -0.07
    POSITIVE LOGITS
    强åĪ¶
    0.07
    强åĪ¶æĢ§
    0.07
    åħ¨
    0.07
     Xxx
    0.06
    人æķ°
    0.06
    éĻIJåĪ¶
    0.06
    .Inner
    0.06
    rig
    0.06
     restrictions
    0.06
    uced
    0.06
    Activations Density 0.001%

    No Known Activations