© 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. 3749
    Prev
    Next
    INDEX
    Explanations

    counting values or items

    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
    éĢģä¸Ģ
    -0.08
    cep
    -0.08
    ModelError
    -0.07
    æĪ·æĪ·
    -0.07
    ordial
    -0.07
    以ä¸Ģ
    -0.07
    vd
    -0.07
    éģĵéģĵ
    -0.07
    个ä½ĵ
    -0.07
    istico
    -0.07
    POSITIVE LOGITS
    .filtered
    0.12
     Subset
    0.12
     filtered
    0.11
     subset
    0.11
     selectively
    0.11
    _filtered
    0.11
    Filtered
    0.10
    çŃĽéĢī
    0.10
    Subset
    0.10
    对éĤ£äºĽ
    0.09
    Activations Density 0.247%

    No Known Activations