© 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. 12127
    Prev
    Next
    INDEX
    Explanations

    instead of

    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
    渺
    -0.06
     defines
    -0.06
    öst
    -0.06
    mitt
    -0.06
    indel
    -0.06
     continuo
    -0.06
    å§
    -0.06
    openid
    -0.06
    ä¸ŃåİŁ
    -0.06
    lando
    -0.06
    POSITIVE LOGITS
    AndWait
    0.08
    RELATED
    0.08
    ponge
    0.07
    æĮ½çķĻ
    0.07
    +')
    0.07
    +")
    0.07
    zej
    0.07
    èĢĥ
    0.07
    rypton
    0.07
    èĢĥäºĨ
    0.07
    Activations Density 0.006%

    No Known Activations