© 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. 29452
    Prev
    Next
    INDEX
    Explanations

    told the Radio

    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
    empf
    -0.08
    æĢ§åħ³èĬĤçĤİ
    -0.08
    ades
    -0.07
    éĶ¦æ¶Ľ
    -0.07
     ACTIONS
    -0.07
    çī¹
    -0.07
    å¸ĮæľĽå¯¹å¤§å®¶
    -0.07
    hir
    -0.07
    -char
    -0.07
    æıIJåıĸ
    -0.07
    POSITIVE LOGITS
     ours
    0.06
     SA
    0.06
     izman
    0.06
     Silvio
    0.06
    ä¸ŃåĽ½çī¹èī²
    0.05
     M
    0.05
     subs
    0.05
     .
    0.05
    å´½
    0.05
    angel
    0.05
    Activations Density 2.337%

    No Known Activations