© 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. 57693
    Prev
    Next
    INDEX
    Explanations

    convention

    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
    rie
    -0.08
    åľŁèĢ³
    -0.07
    åħįè´¹åıijå¸ĥ
    -0.07
    å§ĶåĨħ
    -0.07
     ÑģÑĩеÑĤÑĥ
    -0.07
    æľĢæĸ°åıijå¸ĥ
    -0.06
    éĵ¡
    -0.06
     Extr
    -0.06
    éĤ£æŶ
    -0.06
    欢è¿İæĿ¥åĪ°
    -0.06
    POSITIVE LOGITS
    év
    0.09
     none
    0.09
    none
    0.08
    pector
    0.08
    úc
    0.08
    åŀĴ
    0.07
    ä¸īåħ«
    0.07
    :none
    0.07
    âu
    0.07
    .none
    0.07
    Activations Density 0.186%

    No Known Activations