© 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. 18495
    Prev
    Next
    INDEX
    Explanations

    code package declarations

    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
    ↵            ↵
    -0.06
    :
    -0.06
    uesa
    -0.06
    çĬ¶åĨµ
    -0.06
    æł¹æľ¬å°±ä¸į
    -0.06
    éĿ¢å¯¹çĿĢ
    -0.06
    uae
    -0.06
    <|fim_prefix|>
    -0.06
     Mitra
    -0.06
    âij
    -0.06
    POSITIVE LOGITS
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.08
    延伸éĺħ读
    0.08
    ĵĺ
    0.08
    .defaultProps
    0.08
    ArrayOf
    0.08
    ressing
    0.07
    æľªå®Įå¾ħç»Ń
    0.07
    æĶĺ
    0.07
    æĬ¤çIJĨå·¥ä½ľ
    0.07
    _unused
    0.07
    Activations Density 0.829%

    No Known Activations