© 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. 12409
    Prev
    Next
    INDEX
    Explanations

    polychlorinated biphenyls

    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
     اØŃ
    -0.07
    æĿĸ
    -0.07
    avra
    -0.07
    ophone
    -0.07
    ihil
    -0.07
    æ²IJ
    -0.07
     Trot
    -0.07
    ç¾Ĭ
    -0.06
    usalem
    -0.06
    ophon
    -0.06
    POSITIVE LOGITS
    è¶ħæłĩ
    0.08
    èĥģ
    0.08
     ubiquitous
    0.08
    çļĦåį±å®³
    0.08
    åĨħåĪĨæ³Į
    0.08
     detections
    0.08
     widespread
    0.08
    æ®ĥ
    0.08
    æĹłå¤Ħä¸įåľ¨
    0.08
    ÑħÑĤа
    0.07
    Activations Density 0.139%

    No Known Activations