© 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. 50593
    Prev
    Next
    INDEX
    Explanations

    but, albeit, not, wherein

    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
    rasz
    -0.08
     ë¬¼ë¡ł
    -0.08
    verts
    -0.08
     dessus
    -0.08
    geist
    -0.08
     constantemente
    -0.08
    Ãłi
    -0.07
    Ø©
    -0.07
    লà§įপ
    -0.07
    unek
    -0.07
    POSITIVE LOGITS
     which
    0.10
    **
    0.10
    which
    0.08
    æ¯Ľæ³½ä¸ľæĢĿæĥ³
    0.08
    åĭĩå¾Ģ缴åīį
    0.08
     and
    0.07
    对åIJ§
    0.07
    以åıĬ
    0.07
    im
    0.07
     albeit
    0.07
    Activations Density 0.041%

    No Known Activations