© 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. 64310
    Prev
    Next
    INDEX
    Explanations

    post navigation

    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
    hi
    -0.07
    .jackson
    -0.07
    ä¹ĭä¹ħ
    -0.06
    af
    -0.06
    ôi
    -0.06
    åĽłç´łçļĦ
    -0.06
    çĶŁæ´»çĶ¨åĵģ
    -0.06
     **.**
    -0.06
     Enlightenment
    -0.06
    acro
    -0.06
    POSITIVE LOGITS
    obet
    0.08
    IGATION
    0.07
    å·¥ä½ľéľĢè¦ģ
    0.07
    onale
    0.07
    æĪijä¹Łè¦ģ
    0.07
     Bong
    0.07
    atology
    0.06
    éken
    0.06
    onet
    0.06
    殿åłĤ
    0.06
    Activations Density 0.001%

    No Known Activations