© 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. 33360
    Prev
    Next
    INDEX
    Explanations

    self-compound words

    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
    semb
    -0.09
    rawdÄĻ
    -0.09
    quisitions
    -0.08
    ãģĺãĤģãģ¦
    -0.08
    èĩªå·±çļĦåĬªåĬĽ
    -0.07
    -chief
    -0.07
    ulty
    -0.07
    fertig
    -0.07
    anyak
    -0.07
    idez
    -0.07
    POSITIVE LOGITS
    verständlich
    0.14
    s
    0.12
    hood
    0.11
    ändig
    0.10
    lessness
    0.10
    ständig
    0.09
    sWith
    0.09
    t
    0.09
    paced
    0.08
    تاÙĨ
    0.08
    Activations Density 0.040%

    No Known Activations