© 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. 3442
    Prev
    Next
    INDEX
    Explanations

    definitions and facts

    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
     obviously
    -0.07
    åħįåĨł
    -0.06
     Obviously
    -0.06
     hopefully
    -0.06
    1
    -0.06
    åĩĨ
    -0.06
    -
    -0.06
    3
    -0.06
    uk
    -0.06
    ä»»ä½ķ责任
    -0.06
    POSITIVE LOGITS
    reti
    0.10
    letal
    0.09
    èªķ
    0.09
    onos
    0.09
    CHED
    0.08
    åıĪ称为
    0.08
    .gov
    0.08
    egah
    0.08
    tene
    0.08
    STALL
    0.08
    Activations Density 0.001%

    No Known Activations