© 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. 27709
    Prev
    Next
    INDEX
    Explanations

    evening before, standards they, separation from

    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
     accordingly
    -0.08
    canf
    -0.08
    ä»ħæѤ
    -0.08
    è¿ĻæŶçļĦ
    -0.07
    urgia
    -0.07
    缸åħ³æݨèįIJ
    -0.07
     thereafter
    -0.07
    ffset
    -0.07
    çĶ±æѤ
    -0.07
    对æѤ
    -0.07
    POSITIVE LOGITS
    æŁIJæŁIJ
    0.07
    è¿ĺä¸įå¦Ĥ
    0.07
    éĥ½æĺ¯èĩªå·±
    0.07
    å°±ä¸Ģå®ļè¦ģ
    0.07
     conduc
    0.07
    èĢĮæŃ»
    0.07
    åĥıä½ł
    0.07
    æ¯Ķä½ł
    0.07
    ä¸Ģå®ļè¦ģæľī
    0.07
    èĢĮ导èĩ´
    0.06
    Activations Density 0.451%

    No Known Activations