© 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. 51111
    Prev
    Next
    INDEX
    Explanations

    little followed by a noun or adverb

    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
    worthy
    -0.11
    à¯įà®ķ
    -0.10
    ableView
    -0.09
    urator
    -0.09
    ecchio
    -0.09
    iences
    -0.09
    etime
    -0.09
    asilan
    -0.09
    Äĵr
    -0.09
    illion
    -0.09
    POSITIVE LOGITS
    er
    0.10
    -known
    0.09
    /or
    0.09
    o
    0.08
     volna
    0.08
    Ùĩ
    0.08
    ened
    0.08
     gì
    0.08
    on
    0.07
    u
    0.07
    Activations Density 0.081%

    No Known Activations