© 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. 51837
    Prev
    Next
    INDEX
    Explanations

    company names and news headlines

    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
    ä½ľä¸ºä¸Ģç§į
    -0.08
    çŃīåŁİå¸Ĥ
    -0.07
    åĪĨåĪ«ä¸º
    -0.07
    æĪIJ为ä¸Ģç§į
    -0.07
    çŃīåĽ½å®¶
    -0.07
    è¿Ļç§į
    -0.07
    çŃīåIJĦç§į
    -0.06
    ancel
    -0.06
    ":
    -0.06
    çŃīéĩį大
    -0.06
    POSITIVE LOGITS
     appunto
    0.09
    (which
    0.08
     laquelle
    0.08
     lequel
    0.08
    —which
    0.08
     à¸ĭึà¹Īà¸ĩมี
    0.08
    hias
    0.07
    以åıĬä¸ĢäºĽ
    0.07
    cera
    0.07
    以åıĬåľ¨
    0.07
    Activations Density 0.802%

    No Known Activations