© 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. 11374
    Prev
    Next
    INDEX
    Explanations

    sometimes followed by comma or clause

    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
    sWith
    -0.11
     presumably
    -0.09
     probably
    -0.08
    avais
    -0.08
    ارب
    -0.08
    ãģĬãģĿãĤīãģı
    -0.08
    çĽ¸ä¿¡å¤§å®¶
    -0.08
    swith
    -0.08
     basically
    -0.07
    sofar
    -0.07
    POSITIVE LOGITS
    ìĶ©
    0.13
     бÑĭваеÑĤ
    0.12
    髦
    0.11
     اÙĦØ£ØŃÙĬاÙĨ
    0.10
    ly
    0.10
    fois
    0.10
    çĶļèĩ³æĺ¯
    0.10
    -times
    0.10
     sogar
    0.10
     бÑĭваÑİÑĤ
    0.10
    Activations Density 0.028%

    No Known Activations