© 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. 39570
    Prev
    Next
    INDEX
    Explanations

    multi-layer network or technical terms

    np_acts-logits-general · gemini-2.5-flash-lite

    technical or specialized nouns in formal/academic contexts, particularly in scientific and patent documents.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jrosseruk
    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
    大大çļĦ
    -0.07
    ï
    -0.07
    /or
    -0.06
    \
    -0.06
    Âł
    -0.06
     ï
    -0.06
    .
    -0.06
    ko
    -0.06
    ï¼Ī
    -0.06
    åĬłæĭ¿å¤§
    -0.05
    POSITIVE LOGITS
    ฯ
    0.09
    .opens
    0.08
    anke
    0.08
    ppet
    0.08
     ฯ
    0.08
    ç±³äºļ
    0.08
    ruÄį
    0.08
    æıIJé«ĺæķĪçİĩ
    0.08
    _qs
    0.07
    ç½ĹéĤ£
    0.07
    Activations Density 0.229%

    No Known Activations