© 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. 30182
    Prev
    Next
    INDEX
    Explanations

    ");"

    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
    isien
    -0.09
    veren
    -0.09
    uego
    -0.08
    欢è¿İ大家éĺħ读
    -0.08
    veau
    -0.08
    à¸ĵà¹Į
    -0.08
    abase
    -0.08
    anko
    -0.08
    angkat
    -0.08
    åĴ¨è¯¢æĪij
    -0.08
    POSITIVE LOGITS
    åħ¬çĽĬæĢ§
    0.06
    ä¸įæ¸ħ
    0.06
    2
    0.06
    æŃĩ
    0.06
    ä¸įæĺİ
    0.06
    ikus
    0.05
    !
    0.05
    eko
    0.05
    æŃĮ
    0.05
    è¥
    0.05
    Activations Density 0.039%

    No Known Activations