© 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. 30377
    Prev
    Next
    INDEX
    Explanations

    . please

    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
    ...",
    -0.09
    对åħ¶çľŁå®ŀæĢ§è´Łè´£
    -0.08
    ...',
    -0.08
    z
    -0.08
    åħ¶çī¹å¾ģ
    -0.08
    åħ¶ä¸»è¦ģ
    -0.08
    åħ¶æīĢ
    -0.08
    ...).
    -0.07
    åħ¶åİŁåĽł
    -0.07
    âĢ¦),
    -0.07
    POSITIVE LOGITS
    isser
    0.09
    شت
    0.08
     }
    0.07
    ibble
    0.07
    еÑĤен
    0.07
    akens
    0.07
    áf
    0.07
    Dragging
    0.07
    çī¹åĭĴ
    0.07
    schlag
    0.07
    Activations Density 0.003%

    No Known Activations