© 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. 29898
    Prev
    Next
    INDEX
    Explanations

    second company

    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
    ä»įèĥ½
    -0.07
    æŁı
    -0.07
     distinguished
    -0.07
    abase
    -0.07
    èµ°éģį
    -0.07
    uali
    -0.06
    rome
    -0.06
     fund
    -0.06
    丢
    -0.06
    èĿ´
    -0.06
    POSITIVE LOGITS
    çŃīåħ¶ä»ĸ
    0.11
     ebenfalls
    0.09
    亦çĦ¶
    0.08
    :new
    0.07
    éĤ£è¾¹
    0.07
    vic
    0.07
    èµ·åĪĿ
    0.07
    åĪĿå§ĭ
    0.07
    æݥ管
    0.07
     Gregg
    0.07
    Activations Density 0.190%

    No Known Activations