© 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. 26230
    Prev
    Next
    INDEX
    Explanations

    technical, industrial, or structural concepts

    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
    DebugEnabled
    -0.08
    éĩijå±±
    -0.08
    hyl
    -0.08
    à´£àµį
    -0.07
    nolo
    -0.07
    çģµå±±
    -0.07
    伯æģ©
    -0.07
     **âĸł
    -0.07
    å¯ĮåĬĽ
    -0.07
    æĤ¦
    -0.07
    POSITIVE LOGITS
    æ¯Ķå¦Ĥ
    0.08
    æ¯Ķå¦Ĥåľ¨
    0.08
    çļĦåħ¶ä»ĸ
    0.07
     elsewhere
    0.07
    напÑĢимеÑĢ
    0.07
    å¦Ĥæ°´
    0.07
    该èĤ¡
    0.07
    ä¾ĭãģĪãģ°
    0.07
    ä¾ĭå¦Ĥ
    0.06
    è§Ħå®ļçļĦåħ¶ä»ĸ
    0.06
    Activations Density 0.005%

    No Known Activations