© 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. 19276
    Prev
    Next
    INDEX
    Explanations

    digits and punctuation

    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
     creation
    -0.06
    ç¼Ģ
    -0.06
    RO
    -0.06
     configure
    -0.06
    eman
    -0.05
     configured
    -0.05
     Creation
    -0.05
     equ
    -0.05
    -
    -0.05
    rof
    -0.05
    POSITIVE LOGITS
     Regionale
    0.09
    èĢĮéļıçĿĢ
    0.08
    请åĬł
    0.08
    ëŀĺ
    0.08
    çĶ¨æŶ
    0.08
    kelse
    0.08
    /cat
    0.08
    éļıçĿĢæŶéĹ´çļĦ
    0.08
    è§Ĥæµĭ
    0.08
    åİĨæŶ
    0.08
    Activations Density 0.009%

    No Known Activations