© 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. 3510
    Prev
    Next
    INDEX
    Explanations

    slot, campaign, folder, cash, expire

    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
    aft
    -0.08
    iest
    -0.08
    ascus
    -0.08
    åįĥå¹´
    -0.08
    betes
    -0.07
    zerw
    -0.07
    hipster
    -0.07
    nado
    -0.07
    cito
    -0.07
     СÑĤепа
    -0.07
    POSITIVE LOGITS
    çŃīåħ¶ä»ĸ
    0.09
    è¿Ļåı¯èĥ½æĺ¯
    0.07
    å°Ķå¾·
    0.06
    马è¹Ħ
    0.06
    èĥ½åĬĽçļĦåŁ¹åħ»
    0.06
    صÙģ
    0.06
     Engel
    0.06
     somehow
    0.06
    None
    0.06
    æĪIJæŃ£
    0.06
    Activations Density 0.004%

    No Known Activations