© 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. 45173
    Prev
    Next
    INDEX
    Explanations

    group identifiers

    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
    asil
    -0.08
    å¿Ĩ
    -0.06
    po
    -0.06
    /play
    -0.06
    对æĤ¨
    -0.06
     Mits
    -0.06
    blah
    -0.06
     ‘
    -0.06
     Priv
    -0.06
    ocab
    -0.06
    POSITIVE LOGITS
     infine
    0.09
    ãģĿãģĹãģ¦
    0.08
    çŃīçŃī
    0.08
    èĩ³æĸ¼
    0.08
     enfin
    0.08
    以åıĬ
    0.08
     наконеÑĨ
    0.08
    æĢ»è®¡
    0.07
    åĭĩå¾Ģ缴åīį
    0.07
    çĶļèĢħ
    0.07
    Activations Density 0.028%

    No Known Activations