© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 12415
    Prev
    Next
    INDEX
    Explanations

    AUTO_INCREMENT, partition, crop, clause, protein, code

    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
    .").
    -0.09
    .:**
    -0.09
     («
    -0.08
    ()'
    -0.08
    '**
    -0.08
    <>(
    -0.08
    ";}
    -0.08
    ();//
    -0.08
    thon
    -0.08
    ãĢįï¼Ī
    -0.07
    POSITIVE LOGITS
    lach
    0.07
     extraordinaire
    0.07
    oko
    0.07
    åħ¼
    0.06
    ÙĪØ²
    0.06
    leneck
    0.06
    nej
    0.06
    Nullable
    0.06
    icide
    0.06
    æļ¨
    0.06
    Activations Density 0.053%

    No Known Activations