© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17270
    Prev
    Next
    INDEX
    Explanations

    counter + various suffixes

    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
    èī²åĪĹ
    -0.08
    ãģ£ãģ±
    -0.08
    leine
    -0.08
    tır
    -0.08
    inger
    -0.07
    erness
    -0.07
    itional
    -0.07
    itudes
    -0.07
    ëģĶ
    -0.07
    erge
    -0.07
    POSITIVE LOGITS
    theless
    0.09
    lijke
    0.09
    feit
    0.08
    isle
    0.08
    tement
    0.08
    idge
    0.08
    ой
    0.08
    enance
    0.07
    efs
    0.07
    _than
    0.07
    Activations Density 0.019%

    No Known Activations