© 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. 51261
    Prev
    Next
    INDEX
    Explanations

    I, novel, cryptography, feed, transfer

    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
    ÑĮ
    -0.07
    åıĪ大
    -0.07
    åĩĨ
    -0.07
    icap
    -0.06
    åı£
    -0.06
    urst
    -0.06
    åıĪåľ¨
    -0.06
     promet
    -0.06
    åħĪè¡Į
    -0.06
    为大家
    -0.06
    POSITIVE LOGITS
    cken
    0.09
    ãģĹãģ¾ãģĽãĤĵ
    0.09
    ãģĤãģı
    0.09
    ãĤĢãģĹãĤį
    0.08
    ä¸İæѤ
    0.08
    igni
    0.08
     justru
    0.08
     raczej
    0.08
    кеÑĢа
    0.08
    并ä¸į
    0.08
    Activations Density 0.005%

    No Known Activations