© 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. 32342
    Prev
    Next
    INDEX
    Explanations

    flap inset

    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
    unge
    -0.06
    ä¸İæѤ
    -0.06
    ukat
    -0.06
    vere
    -0.06
    èī¯æĢ§
    -0.06
     Studi
    -0.06
     Bub
    -0.06
    .Compile
    -0.06
    eger
    -0.06
    amad
    -0.06
    POSITIVE LOGITS
    åľ¨ä¸Ĭè¿°
    0.08
    éĹ»
    0.08
    èģŀ
    0.08
    åĴĮæ´»åĬ¨
    0.07
    éĥ¨éĹ¨è´Łè´£äºº
    0.07
    agog
    0.07
    ftar
    0.07
    çĻĸ
    0.07
     readline
    0.07
    å°Ķé¡¿
    0.07
    Activations Density 0.511%

    No Known Activations