© 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. 61039
    Prev
    Next
    INDEX
    Explanations

    unique identifiers or codes

    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
    aliza
    -0.08
    å¤Ħ女
    -0.08
    -contrib
    -0.07
    /general
    -0.07
    缸å¾ħ
    -0.07
    aline
    -0.07
    åľ°çIJĨä½įç½®ä¼ĺè¶Ĭ
    -0.07
    å¯ĮåIJ«ç»´çĶŁç´ł
    -0.06
    _CONFIGURATION
    -0.06
    headed
    -0.06
    POSITIVE LOGITS
    åı·
    0.11
    åı·çļĦ
    0.11
    åı·åĴĮ
    0.10
    åı·çłģ
    0.10
    /name
    0.10
    èĻŁ
    0.09
     unik
    0.09
     unique
    0.09
    entifier
    0.09
    ë²Ī
    0.09
    Activations Density 0.384%

    No Known Activations