© 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. 43212
    Prev
    Next
    INDEX
    Explanations

    not always

    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
    ä¸įåIJ«
    -0.11
    ä¸Ń没æľī
    -0.10
    ä¸įçĶ¨åĨį
    -0.09
    æľªå¿ħ
    -0.09
    ä¸įæ±Ĥ
    -0.09
    ä¸įåĨįæľī
    -0.09
    ä¸įæ¶īåıĬ
    -0.09
    没æľīä»»ä½ķ
    -0.09
     devoid
    -0.09
     without
    -0.09
    POSITIVE LOGITS
    èĢĮæĺ¯
    0.18
    èĢĮæĺ¯è¦ģ
    0.14
    èĢĮæĺ¯åľ¨
    0.13
     sondern
    0.12
     melainkan
    0.12
     بÙĦÚ©Ùĩ
    0.12
    èĢĮæĺ¯ä¸Ģ个
    0.11
    èĢĮæĺ¯ä¸Ģç§į
    0.10
    èĢĮåľ¨äºİ
    0.10
     hanem
    0.09
    Activations Density 0.170%

    No Known Activations