© 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. 55717
    Prev
    Next
    INDEX
    Explanations

    introducing variables

    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
    æłĸéľŀ
    -0.07
    çī¹å®ļçļĦ
    -0.07
     Jr
    -0.07
    çī¹å®ļ
    -0.07
    .IGNORE
    -0.07
    gina
    -0.06
    å¥ĩçŁ³
    -0.06
    æIJŀå¾Ĺ
    -0.06
    åĪ°åºķ
    -0.06
    EXPORT
    -0.06
    POSITIVE LOGITS
    çŃĶ
    0.10
    æľ¬é¢ĺ
    0.08
    é¡Į
    0.08
    æľ¬é¢ĺèĢĥæŁ¥
    0.08
    asca
    0.08
    AMB
    0.08
    åĽłçĪ²
    0.08
    çķ¥
    0.07
    å¦ĤåĽ¾æīĢ示
    0.07
    è¿ĺèĥ½å¤Ł
    0.07
    Activations Density 0.010%

    No Known Activations