© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 47101
    Prev
    Next
    INDEX
    Explanations

    Error or technical terms

    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
    ัà¸Ļà¸Ĺ
    -0.08
    imson
    -0.08
    å®Ŀå±±
    -0.08
    åħ¶çľŁå®ŀæĢ§
    -0.07
    oreach
    -0.07
    holt
    -0.07
    Marc
    -0.07
    ì°©
    -0.07
    és
    -0.07
    lick
    -0.07
    POSITIVE LOGITS
    æķ´ä½ĵ
    0.06
    uges
    0.06
    igy
    0.06
     overall
    0.06
    type
    0.06
    èľľ
    0.06
    igin
    0.06
    /env
    0.06
    éĩľ
    0.06
    åħħåĪĨè°ĥåĬ¨
    0.06
    Activations Density 0.001%

    No Known Activations