© 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. 24514
    Prev
    Next
    INDEX
    Explanations

    names followed by places or titles

    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
    romium
    -0.08
    æĺ¥ç¬ĭ
    -0.08
    asaran
    -0.08
     ÐłÐļ
    -0.07
    enville
    -0.07
    Expose
    -0.07
    otts
    -0.07
     nisso
    -0.07
    ÙĪÛĮÛĮ
    -0.07
    JECT
    -0.07
    POSITIVE LOGITS
    ↵↵
    0.06
    ::-
    0.06
    ander
    0.05
    <|endoftext|>
    0.05
    ital
    0.05
    ÙĪØ·
    0.05
     bra
    0.05
    oul
    0.05
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.05
     âĪĴ
    0.05
    Activations Density 1.532%

    No Known Activations