© 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. 8132
    Prev
    Next
    INDEX
    Explanations

    This or fails

    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
    leit
    -0.07
     plenty
    -0.07
     sang
    -0.06
    åĽĽæĸ¹
    -0.06
    ibia
    -0.06
    _FUN
    -0.06
    sung
    -0.06
     liber
    -0.06
     Plenty
    -0.06
    ole
    -0.06
    POSITIVE LOGITS
    åį´ä¸įèĥ½
    0.10
    åį´åĽłä¸º
    0.10
    ä¸į建议
    0.09
    ä½ľåĪĻ
    0.09
    èĻ½çĦ¶æľī
    0.09
    öö
    0.08
    fails
    0.08
     fails
    0.08
    ième
    0.08
    éĹ®é¢ĺæĿ¥äºĨ
    0.08
    Activations Density 0.064%

    No Known Activations