© 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. 13325
    Prev
    Next
    INDEX
    Explanations

    file/events/time

    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
    æŶæĹł
    -0.07
    éĻĦ
    -0.07
    isma
    -0.07
    abis
    -0.07
    æĹ¶ä¸º
    -0.07
     public
    -0.06
    _COMPARE
    -0.06
    ITO
    -0.06
    以åħį
    -0.06
    ä½ķåľ°
    -0.06
    POSITIVE LOGITS
    ux
    0.07
    åį§
    0.07
    èĢĢ
    0.07
    ÙĬÙĨØ©
    0.07
    onda
    0.06
    chia
    0.06
    å²³
    0.06
    oston
    0.06
    slots
    0.06
    ;
    0.06
    Activations Density 0.081%

    No Known Activations