© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39712
    Prev
    Next
    INDEX
    Explanations

    anthracene

    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
    ulat
    -0.07
    髦
    -0.07
    æīĭèħķ
    -0.07
    sang
    -0.06
    åīįç½®
    -0.06
     Gag
    -0.06
     каб
    -0.06
    ewa
    -0.06
    erval
    -0.06
    æıĴèĬ±
    -0.06
    POSITIVE LOGITS
     cigaret
    0.09
    çĥĥ
    0.07
    çħ¤çĤŃ
    0.07
    osamente
    0.07
    çĥ¯
    0.07
    enic
    0.07
    äºĮåįģä¹Ŀ
    0.07
    обен
    0.07
    вл
    0.07
    wick
    0.07
    Activations Density 0.043%

    No Known Activations