© 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. 14500
    Prev
    Next
    INDEX
    Explanations

    file paths and method calls

    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
    è©°
    -0.07
    èĩ£
    -0.07
    åģļ为
    -0.07
    è¿Ļ个æĺ¯
    -0.07
     Fortun
    -0.06
    天æĺİ
    -0.06
    ogna
    -0.06
    rees
    -0.06
    ÑĢей
    -0.06
     eingeb
    -0.06
    POSITIVE LOGITS
    etos
    0.08
    ÅĨ
    0.07
    è¿ĶåĽŀåĪĹ表
    0.07
    onos
    0.07
    zion
    0.07
    çĤ¹åĪ°
    0.07
    emoc
    0.07
    ç¾İæĸĩ
    0.07
    çĤ¹å¯¹
    0.07
    innen
    0.06
    Activations Density 0.392%

    No Known Activations