© 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. 58472
    Prev
    Next
    INDEX
    Explanations

    per serving, per carton, per rat, per kilogram, per execution, per person

    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
    dl
    -0.08
    gn
    -0.07
    ä¾ł
    -0.07
    tro
    -0.07
    èĩ£
    -0.07
    ruise
    -0.07
    ora
    -0.07
    注æĦıäºĨ
    -0.07
    _MALLOC
    -0.07
    zl
    -0.07
    POSITIVE LOGITS
     اÙĦÙĪا
    0.11
    ocale
    0.08
    ugend
    0.07
    /license
    0.07
     اÙĦÙĪاØŃد
    0.07
    éĻħ
    0.07
     기ì¤Ģìľ¼ë¡ľ
    0.07
    áºŃu
    0.07
     basis
    0.07
    à¤Ń
    0.06
    Activations Density 0.035%

    No Known Activations