© 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. 20462
    Prev
    Next
    INDEX
    Explanations

    statements of personal need or intent

    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
    èĨ
    -0.06
     arguably
    -0.06
    odik
    -0.06
    å¾Ĺåħ¶
    -0.06
    pek
    -0.06
    åıįèĢĮæĺ¯
    -0.06
    orso
    -0.06
    लय
    -0.06
    åĿĩä»·
    -0.06
    alan
    -0.06
    POSITIVE LOGITS
    æŁIJæŁIJ
    0.14
     blah
    0.11
     xxx
    0.10
    XXX
    0.10
    XX
    0.10
    xxx
    0.10
    XXXX
    0.09
     XYZ
    0.09
    çľĭæĪij
    0.09
    ez
    0.09
    Activations Density 0.335%

    No Known Activations