© 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. 45492
    Prev
    Next
    INDEX
    Explanations

    locked, paradox, stal, ideal, solutions

    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
    ben
    -0.07
     emplois
    -0.07
    irme
    -0.06
    æľ¬èģĮ
    -0.06
    IndexOf
    -0.06
    娥
    -0.06
    idor
    -0.06
    utz
    -0.06
    бе
    -0.06
    次åħĥ
    -0.06
    POSITIVE LOGITS
    éĢļ天
    0.07
    akwa
    0.07
    raud
    0.07
    rou
    0.07
    åħįè´¹åıijå¸ĥ
    0.07
    کت
    0.07
    ä¸ŃéĢļ
    0.07
    èĵĸ
    0.07
    seau
    0.07
    recht
    0.07
    Activations Density 0.009%

    No Known Activations