© 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. 3683
    Prev
    Next
    INDEX
    Explanations

    Rodriguez, solvent, introspective

    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
    impin
    -0.09
    enius
    -0.08
    èıľåĽŃ
    -0.08
    ingan
    -0.08
    ä¸ĢèģĬ
    -0.08
    éĶ¦æĹĹ
    -0.07
     orto
    -0.07
    onet
    -0.07
     kenn
    -0.07
    ä¸Ģå±Ĭ
    -0.07
    POSITIVE LOGITS
    è§ģ人
    0.06
    ä½ĨæľĢç»Ī
    0.06
    åħ¬
    0.06
    åĪĨåĮħ
    0.06
    ÑĢоб
    0.06
    ä¸įåı¯éģ¿åħįåľ°
    0.06
    ocere
    0.06
    ç³»
    0.06
    Bound
    0.06
    .googleapis
    0.06
    Activations Density 0.003%

    No Known Activations