© 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. 20672
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with parentheses and numbers

    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
    pl
    -0.06
    ent
    -0.06
    -R
    -0.06
    ind
    -0.06
    èĹı
    -0.06
     pass
    -0.06
    -t
    -0.06
     ind
    -0.06
     Ref
    -0.06
    奴
    -0.05
    POSITIVE LOGITS
    -loader
    0.08
    chin
    0.08
    INAN
    0.08
    ç¡ķ
    0.08
    lager
    0.08
     attribution
    0.08
    _charset
    0.08
    Chunk
    0.08
    zos
    0.08
     extrém
    0.07
    Activations Density 0.240%

    No Known Activations