© 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. 14203
    Prev
    Next
    INDEX
    Explanations

    formalin-fixed, preservation, samples

    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
    avan
    -0.09
    Retry
    -0.07
     reclaimed
    -0.07
    åĨ³æĪĺ
    -0.07
    _PLATFORM
    -0.07
    çIJ¦
    -0.07
    _ro
    -0.06
    åѵ
    -0.06
    สู
    -0.06
    _UD
    -0.06
    POSITIVE LOGITS
    ä¿ĿåŃĺ
    0.15
     preservation
    0.15
     preserving
    0.14
    æįķèİ·
    0.14
     preserves
    0.14
     preserve
    0.13
     capture
    0.13
     preserv
    0.13
    preserve
    0.12
     preserved
    0.12
    Activations Density 0.097%

    No Known Activations