© 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. 46033
    Prev
    Next
    INDEX
    Explanations

    financial matters

    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
    -fashioned
    -0.08
     fashioned
    -0.08
    ed
    -0.07
    оÑĢо
    -0.07
    gaard
    -0.07
    財ç¶ĵ
    -0.07
    å¢ħ
    -0.07
    ÙĪØ©
    -0.07
    k
    -0.07
    ductory
    -0.07
    POSITIVE LOGITS
    å¸
    0.08
    fulness
    0.08
    tright
    0.08
    ièrement
    0.08
    isbury
    0.08
    agli
    0.08
    ielen
    0.08
    mente
    0.08
    çĶ¥
    0.08
    ingen
    0.08
    Activations Density 0.024%

    No Known Activations