© 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. 39935
    Prev
    Next
    INDEX
    Explanations

    north-east

    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
    lix
    -0.09
    ogn
    -0.07
     alike
    -0.07
    导
    -0.07
    éĶĻè§ī
    -0.06
    究
    -0.06
    京
    -0.06
    mel
    -0.06
    çĪ½
    -0.06
    oudre
    -0.06
    POSITIVE LOGITS
    .addTo
    0.10
    æ·»åĬłåĪ°
    0.09
    åĬłåħ¥
    0.09
    addTo
    0.09
     adds
    0.08
    æ·»åĬł
    0.08
     added
    0.08
     addition
    0.08
    æľī家
    0.08
     adding
    0.08
    Activations Density 0.001%

    No Known Activations