© 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. 43152
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives and follow-up nouns

    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
    unan
    -0.07
    untu
    -0.07
    以赴
    -0.07
    轩
    -0.07
    undra
    -0.07
    tagen
    -0.06
    iegu
    -0.06
    uket
    -0.06
    éļıçĿĢå¹´é¾Ħ
    -0.06
    ients
    -0.06
    POSITIVE LOGITS
    çŃīçŃī
    0.11
    å·¥ç¨ĭçŃī
    0.10
    管çIJĨçŃī
    0.09
    æ³ķçŃī
    0.09
     insomma
    0.09
     enfin
    0.08
     sonstige
    0.08
    ä¸Ńå¿ĥçŃī
    0.08
    etc
    0.08
    åħ¶å®ĥ
    0.08
    Activations Density 0.750%

    No Known Activations