© 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. 31384
    Prev
    Next
    INDEX
    Explanations

    code block delimiters

    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
    i
    -0.08
    I
    -0.07
    ãĢĢ
    -0.06
    ignano
    -0.06
    er
    -0.06
    um
    -0.06
    ily
    -0.06
    çļĦæĹ¥åŃIJ
    -0.06
    çļĦéĩį
    -0.06
    Äĥt
    -0.06
    POSITIVE LOGITS
    å¨ĥ
    0.08
    ull
    0.08
     Crian
    0.08
    ÙĪد
    0.07
    rippling
    0.07
    ripp
    0.07
    ippo
    0.07
    ñera
    0.07
    OGO
    0.07
    壮大çļĦ
    0.07
    Activations Density 0.126%

    No Known Activations