© 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. 9316
    Prev
    Next
    INDEX
    Explanations

    what is issued

    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
     merc
    -0.07
    以ä¸Ĭ
    -0.06
    æĢİä¹ĪåĬŀåij¢
    -0.06
    èĩ³å°ijæľī
    -0.06
    ajte
    -0.06
     wherever
    -0.06
    åıªæľīä¸Ģ个
    -0.06
    7
    -0.06
     tous
    -0.06
    ä»Ģä¹Īåij¢
    -0.06
    POSITIVE LOGITS
    à¸ļà¹īาà¸ĩ
    0.16
    以åıĬå¦Ĥä½ķ
    0.15
     ÙĪÙĥÙĬÙģ
    0.15
     ÙĪØ£ÙĬ
    0.11
    à¹Ħหà¸Ļ
    0.11
    /how
    0.10
    ä½ķåľ°
    0.10
     poszczegól
    0.10
    åĵªäºĽ
    0.10
    ä¸Ģ缮äºĨçĦ¶
    0.09
    Activations Density 0.171%

    No Known Activations