© 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. 7515
    Prev
    Next
    INDEX
    Explanations

    element multiplication

    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
    ×Ļ×ķת
    -0.07
    urin
    -0.07
     pains
    -0.06
    ÙĬÙĨ
    -0.06
    UPER
    -0.06
    WARDS
    -0.06
    踵
    -0.06
     tendon
    -0.06
    anko
    -0.06
    umon
    -0.06
    POSITIVE LOGITS
    TXT
    0.08
    elf
    0.08
     Wiss
    0.07
    -prepend
    0.07
    iband
    0.07
    çĻ¾åĪĨä¹ĭçĻ¾
    0.07
    å±Ģéĥ¨
    0.07
    ãģıãĤĮãģ¦
    0.07
    éļľ
    0.07
     Æ¡i
    0.07
    Activations Density 0.010%

    No Known Activations