© 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. 18924
    Prev
    Next
    INDEX
    Explanations

    character and size limits

    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
    xBC
    -0.09
    xBB
    -0.09
    iya
    -0.08
    eroy
    -0.08
    rezz
    -0.08
    xFB
    -0.08
    xCD
    -0.08
    correo
    -0.08
    åIJİåį³
    -0.08
    aleur
    -0.08
    POSITIVE LOGITS
     limitation
    0.09
    ä¸ĬéĻIJ
    0.09
     Limit
    0.09
     limit
    0.09
    éĻIJ
    0.09
    ä¸įå¾Ĺè¶ħè¿ĩ
    0.09
    éĻIJäºİ
    0.08
    以åĨħ
    0.08
     limited
    0.08
    Limit
    0.08
    Activations Density 0.181%

    No Known Activations