© 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. 41868
    Prev
    Next
    INDEX
    Explanations

    sodium compounds

    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
     latter
    -0.08
    ned
    -0.07
    patrick
    -0.07
    agg
    -0.07
    ter
    -0.07
    chaft
    -0.07
    che
    -0.06
    der
    -0.06
    fts
    -0.06
    anca
    -0.06
    POSITIVE LOGITS
    utilus
    0.09
    iento
    0.08
    orsk
    0.08
    udah
    0.08
    ughter
    0.08
    åĽŀäºĭ
    0.08
    romo
    0.08
    jenigen
    0.08
    য়
    0.08
    orit
    0.08
    Activations Density 0.017%

    No Known Activations