© 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. 33291
    Prev
    Next
    INDEX
    Explanations

    thoughts, thought process, thought exercises

    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
    ities
    -0.12
    ussion
    -0.11
    psilon
    -0.11
    jenigen
    -0.10
    IMUM
    -0.10
    <|box_end|>
    -0.10
    ãģĹãĤĤ
    -0.09
    ation
    -0.09
    oftware
    -0.09
    istrator
    -0.09
    POSITIVE LOGITS
    fulness
    0.10
    iness
    0.10
    edly
    0.09
    zelfde
    0.09
    en
    0.08
    t
    0.08
    ypes
    0.08
    elijke
    0.08
    ers
    0.08
    人
    0.08
    Activations Density 0.122%

    No Known Activations