© 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. 62132
    Prev
    Next
    INDEX
    Explanations

    fulfil a request

    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
    ιÏİ
    -0.08
    æĢĢæĬ±
    -0.08
    pliers
    -0.07
    ouz
    -0.07
    ãĥ¼ãĤ¯
    -0.07
     Afinal
    -0.07
    æľĹ
    -0.07
    æ°¸åĪ©
    -0.07
     Confira
    -0.07
    åį³æĹ¥èµ·èĩ³
    -0.07
    POSITIVE LOGITS
    客æĪ·è¦ģæ±Ĥ
    0.10
     requests
    0.09
    éľĢè¦ģæıIJä¾Ľ
    0.09
    çļĦ请æ±Ĥ
    0.09
     request
    0.08
     prompted
    0.08
    Requested
    0.08
    YP
    0.08
     summons
    0.08
     requested
    0.07
    Activations Density 0.467%

    No Known Activations