© 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. 32429
    Prev
    Next
    INDEX
    Explanations

    age descriptions

    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
    æĵį
    -0.07
    anz
    -0.07
    _ins
    -0.06
    vez
    -0.06
    ев
    -0.06
    amed
    -0.06
     Alonso
    -0.06
     enough
    -0.06
     Otherwise
    -0.06
    ↵
    -0.06
    POSITIVE LOGITS
    çĶļèĩ³æ¯Ķ
    0.10
    åĬ¨è¾Ħ
    0.10
     even
    0.09
    çĶļèĩ³
    0.09
    çĶļèĩ³åľ¨
    0.09
     apalagi
    0.09
    çĶļèĩ³æľī
    0.08
    çĶļèĩ³æĺ¯
    0.08
    even
    0.08
    åį³ä¾¿æĺ¯
    0.08
    Activations Density 0.062%

    No Known Activations