© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21868
    Prev
    Next
    INDEX
    Explanations

    file types and related actions

    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
    adin
    -0.10
    otec
    -0.08
    åĿıçļĦ
    -0.08
    ersen
    -0.07
    жин
    -0.07
    æľī害
    -0.07
    eson
    -0.07
    idio
    -0.07
    _ANAL
    -0.07
    IEWS
    -0.07
    POSITIVE LOGITS
    æį®æѤ
    0.12
     accordingly
    0.09
    åĽłæѤèĢĮ
    0.09
    ä¹ŁåĽłæѤ
    0.09
    çĶ±æѤ
    0.08
    以æŃ¤ä¸º
    0.07
     consequently
    0.07
    eger
    0.07
    以æѤ
    0.07
    缸åºĶ
    0.07
    Activations Density 0.195%

    No Known Activations