© 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. 63512
    Prev
    Next
    INDEX
    Explanations

    price, geld, change

    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
    -0.08
    ically
    -0.06
    ä¸įåİĮ
    -0.06
    <|endoftext|>
    -0.05
    ized
    -0.05
    ä¸Ģéģį
    -0.05
    ually
    -0.05
    ally
    -0.05
    .
    -0.05
    [
    -0.05
    POSITIVE LOGITS
    临éŨ
    0.09
    ontos
    0.08
    -animate
    0.08
    Ñģполни
    0.08
    åĻ¨
    0.08
    ivre
    0.08
    åħĭç¦ı
    0.08
    à¸ģà¹Į
    0.08
     shouldBe
    0.08
    enschaft
    0.08
    Activations Density 0.064%

    No Known Activations