© 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. 40009
    Prev
    Next
    INDEX
    Explanations

    born in

    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
    USTER
    -0.06
     shy
    -0.06
    ÏĦÏİ
    -0.06
    人çĶŁ
    -0.06
    奴
    -0.06
    åįģ天
    -0.06
    rts
    -0.06
    ify
    -0.06
    å½ĵåīį
    -0.06
    gan
    -0.06
    POSITIVE LOGITS
    èĩªå·±èº«ä¸Ĭ
    0.08
    å°Ķ夫
    0.07
    ếm
    0.07
    watan
    0.07
    æ°§åĮĸ碳
    0.07
     combusti
    0.07
    ldata
    0.07
    ÐĹÐŀ
    0.07
    xCD
    0.07
     ejak
    0.07
    Activations Density 0.328%

    No Known Activations