© 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. 22183
    Prev
    Next
    INDEX
    Explanations

    model theory language

    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
    å¹ħ
    -0.06
    æĹłåģ¿çĮ®è¡Ģ
    -0.06
     ven
    -0.06
    èģĨ
    -0.06
    éĻįåİĭ
    -0.06
     конвеÑĢ
    -0.06
    å¦ĤåĽł
    -0.06
     unlaw
    -0.06
    etim
    -0.06
    èĦĬæ¢ģ
    -0.06
    POSITIVE LOGITS
    .predicate
    0.09
    ificante
    0.08
     predicate
    0.08
     predicates
    0.08
    _INFINITY
    0.08
    åıĤ天
    0.08
     schemas
    0.08
    andid
    0.08
    ipp
    0.08
    -language
    0.08
    Activations Density 0.012%

    No Known Activations