© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 49926
    Prev
    Next
    INDEX
    Explanations

    noble gases, electronic, mimicry

    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
    chants
    -0.09
    åħ¨åı°
    -0.08
    ãģ«å¾ĵ
    -0.08
    plitude
    -0.08
    çļĦ主è§Ĥ
    -0.08
    ctors
    -0.08
    á»ıng
    -0.07
    Ñĥди
    -0.07
    pte
    -0.07
     fár
    -0.07
    POSITIVE LOGITS
    壳
    0.07
    _embed
    0.07
     поко
    0.07
     likeness
    0.06
     shell
    0.06
     bombard
    0.06
    å¡ŀ
    0.06
    ä½ĵ
    0.06
    shell
    0.06
    _restore
    0.06
    Activations Density 0.002%

    No Known Activations