© 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. 12804
    Prev
    Next
    INDEX
    Explanations

    their needs

    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¸Ģ举
    -0.07
    ØŃØ©
    -0.07
    尤为
    -0.07
    ä»ħåľ¨
    -0.07
    åı¦æľī
    -0.06
    иÑĤоÑĢ
    -0.06
    tw
    -0.06
    _mapping
    -0.06
    alto
    -0.06
    èĢĥè¯ķæĪIJ绩
    -0.06
    POSITIVE LOGITS
    åıªè¦ģæĺ¯
    0.12
    å°±è¡Į
    0.12
    åıªè¦ģèĥ½
    0.11
    åıªè¦ģåľ¨
    0.10
    åıªè¦ģ
    0.09
     sufficiently
    0.09
     reasonably
    0.09
    åıªè¦ģä½ł
    0.09
    çļĦä»»ä½ķ
    0.09
    å°±è¡ĮäºĨ
    0.09
    Activations Density 0.086%

    No Known Activations