© 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. 50205
    Prev
    Next
    INDEX
    Explanations

    Czech Republic

    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
    ido
    -0.06
    pac
    -0.06
    äºīæī§
    -0.06
    åĸĥ
    -0.06
    PROTO
    -0.06
    ill
    -0.06
     tpl
    -0.06
     tij
    -0.05
    èĩªä½ľ
    -0.05
    rob
    -0.05
    POSITIVE LOGITS
    hausen
    0.09
    .house
    0.08
    _GC
    0.08
    cato
    0.08
    chers
    0.08
    ofire
    0.08
    اتب
    0.08
    ptive
    0.08
    .hstack
    0.08
    nowled
    0.07
    Activations Density 0.010%

    No Known Activations