© 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. 42452
    Prev
    Next
    INDEX
    Explanations

    want to know

    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
    èĩªå¸¦
    -0.07
    ppure
    -0.07
    _OPTION
    -0.07
    kers
    -0.07
    -result
    -0.07
    omar
    -0.07
     türlü
    -0.07
     Gutsche
    -0.07
    eway
    -0.07
    portun
    -0.07
    POSITIVE LOGITS
     verify
    0.08
    éªĮè¯ģ
    0.07
    isma
    0.07
    è°¨éĺ²
    0.07
    æł¸å®ŀ
    0.07
     Validate
    0.07
     confirm
    0.07
     validade
    0.07
    确认
    0.07
    åħ·ä½ĵ
    0.07
    Activations Density 0.003%

    No Known Activations