© 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. 57488
    Prev
    Next
    INDEX
    Explanations

    names following commas

    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
    åĢ¶
    -0.08
    Ùģات
    -0.07
    .conf
    -0.07
    pared
    -0.07
    å¤ļèĬ¬
    -0.07
    åĪ°å¤©
    -0.06
    å¤ļ大
    -0.06
    =min
    -0.06
    ocom
    -0.06
    à°¡à±ģ
    -0.06
    POSITIVE LOGITS
    æµıè§Ī次æķ°
    0.08
    Unnamed
    0.07
    åĭķæħĭ
    0.07
    _-_
    0.07
    许
    0.07
    æģª
    0.07
    _ent
    0.07
    .allowed
    0.07
     Ents
    0.06
    æł¼æĭī
    0.06
    Activations Density 0.163%

    No Known Activations