© 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. 49507
    Prev
    Next
    INDEX
    Explanations

    target or desired values

    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
    èıģ
    -0.09
    TypeName
    -0.07
    -scalable
    -0.07
    çī¹å°Ķ
    -0.07
    ijľ
    -0.07
    ìļĶ
    -0.07
    _references
    -0.07
    entially
    -0.07
    ych
    -0.07
    kens
    -0.07
    POSITIVE LOGITS
    /target
    0.09
    å·²ä¹ħçļĦ
    0.09
     values
    0.09
     ëĮĢë¡ľ
    0.08
    éĢļãĤĬãģ«
    0.08
     value
    0.08
    éĢļãĤĬãģ®
    0.08
    åĢ¼
    0.08
    åĢ¼æĺ¯
    0.08
    çļĦéĤ£æł·
    0.07
    Activations Density 0.017%

    No Known Activations