© 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. 56150
    Prev
    Next
    INDEX
    Explanations

    non-english characters

    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
    æĹ©ä¸Ĭ
    -0.06
    bat
    -0.06
    ikian
    -0.06
    箸
    -0.06
    eyer
    -0.06
    å½»
    -0.06
    rava
    -0.06
    ación
    -0.06
    å¤Ħ
    -0.06
    çŃĶæ¡Ī解æŀIJ
    -0.06
    POSITIVE LOGITS
    ä¸ĭæŬ
    0.08
    serrat
    0.08
    äsent
    0.08
    ä¸ĢæĻĥ
    0.08
    afari
    0.07
    æĸ°åĬłåĿ¡
    0.07
    0.07
    uky
    0.07
    нева
    0.07
    ignano
    0.07
    Activations Density 0.040%

    No Known Activations