© 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. 4284
    Prev
    Next
    INDEX
    Explanations

    reportedly working, apparently there are

    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
    åºķ
    -0.07
    /or
    -0.07
    odiac
    -0.07
    bak
    -0.06
    ä¸Ģè§Ĵ
    -0.06
    çļĦåı¯èĥ½æĢ§
    -0.06
    ither
    -0.06
    ymp
    -0.06
    æ²½
    -0.06
     adequately
    -0.06
    POSITIVE LOGITS
    _HAVE
    0.07
    çĻ½çļ®ä¹¦
    0.07
    æ¦
    0.07
    otov
    0.07
    icina
    0.07
    ave
    0.07
    è¶ħå¤ļ
    0.07
    çłĶ究æĺ¾ç¤º
    0.07
    è¿ĻäºĽéĹ®é¢ĺ
    0.07
    æĺ¯è¿Ļæł·
    0.07
    Activations Density 0.012%

    No Known Activations