© 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. 61740
    Prev
    Next
    INDEX
    Explanations

    spock, fits, airline, construct, ridged, throw, agricultural, am

    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
    hek
    -0.09
    ahas
    -0.08
    éf
    -0.08
    oulos
    -0.07
    itos
    -0.07
        ↵↵↵
    -0.07
     admittedly
    -0.07
    人身
    -0.07
     fisi
    -0.07
     avail
    -0.07
    POSITIVE LOGITS
    \n
    0.07
    <br
    0.06
    ¨
    0.06
     &
    0.06
    jung
    0.06
     **
    0.06
    VR
    0.05
    å°İ
    0.05
    rozen
    0.05
    wand
    0.05
    Activations Density 0.002%

    No Known Activations