© 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. 20410
    Prev
    Next
    INDEX
    Explanations

    XML and YAML tags

    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
    NR
    -0.08
    çĶ¨æĪ·å¯¹
    -0.08
    вÑĬ
    -0.08
    úk
    -0.07
    atina
    -0.07
    æ¶ķ
    -0.07
    å¸Ĥåľºå¯¹
    -0.07
    ymp
    -0.07
    zhou
    -0.07
     паÑģÑģ
    -0.07
    POSITIVE LOGITS
    æ¶īå«Į
    0.08
    åĩĮ
    0.07
     mens
    0.06
    ä¸Ģç»ı
    0.06
    put
    0.06
    ä¸Ģä½ľ
    0.06
    ä¸įåĢ¦
    0.06
    æĺŁæľŁäºĶ
    0.06
    第ä¸Ģ款
    0.06
    æ·±åıĹ
    0.06
    Activations Density 0.198%

    No Known Activations