© 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. 2181
    Prev
    Next
    INDEX
    Explanations

    fix itself

    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
    à¹Ģหม
    -0.08
    derland
    -0.08
    èIJį
    -0.08
    ิà¹Īà¸Ļ
    -0.08
    .ONE
    -0.08
    æĬķ
    -0.08
    æŁ
    -0.08
    ramework
    -0.08
    äºĭåıij
    -0.08
    çļĦç¾İèªī
    -0.08
    POSITIVE LOGITS
     itself
    0.06
    eted
    0.06
    ahu
    0.06
     Techn
    0.06
    0.06
    æ´»
    0.06
     Twe
    0.06
    ined
    0.06
    ietf
    0.06
    ahi
    0.05
    Activations Density 0.676%

    No Known Activations