© 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. 26976
    Prev
    Next
    INDEX
    Explanations

    `$lang` quotes code snippets

    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
    alas
    -0.07
    åįĬå±±
    -0.06
    åIJı
    -0.06
    ä¾Ī
    -0.06
    -0.06
    amer
    -0.06
    .ibm
    -0.06
     componentDidMount
    -0.06
    ç³»
    -0.06
    ä»Ĭå¹´
    -0.05
    POSITIVE LOGITS
    #undef
    0.08
    微信æī«ä¸Ģæī«
    0.08
    eer
    0.08
    arca
    0.08
    ä¿¡æģ¯çĶ±
    0.08
    <|repo_name|>
    0.08
    Ĩ
    0.07
    StartPosition
    0.07
    áĢķáĢ¹
    0.07
     Perdana
    0.07
    Activations Density 0.273%

    No Known Activations