© 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. 47572
    Prev
    Next
    INDEX
    Explanations

    storage locations and removed items

    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
    缨
    -0.08
    åľ¨æ°´ä¸Ń
    -0.08
    ç«ĭåľ¨
    -0.07
    å®¶åľ¨
    -0.07
    å§ĭèĩ³
    -0.07
    山人
    -0.07
    åĨĻåľ¨
    -0.07
    æ®ĩ
    -0.07
    idon
    -0.07
    çĤ¹åľ¨
    -0.06
    POSITIVE LOGITS
    æ·±å¤Ħ
    0.10
    éĩĮçļĦ
    0.09
    çŃīå¤Ħ
    0.09
    æ·±å¤ĦçļĦ
    0.08
    ä¸Ń以
    0.08
    ades
    0.08
    éĩĮ
    0.08
    ä¸ŃæĿ¥
    0.08
    aida
    0.07
    -approved
    0.07
    Activations Density 0.380%

    No Known Activations