© 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. 62457
    Prev
    Next
    INDEX
    Explanations

    conversion and shifts

    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
    çĩ
    -0.07
    egend
    -0.07
    积æ·Ģ
    -0.06
    ENCE
    -0.06
    åįĬ身
    -0.06
    å¡ŀ
    -0.06
     sma
    -0.06
     originated
    -0.06
    éģĹ
    -0.06
    æĪ
    -0.06
    POSITIVE LOGITS
    conversion
    0.09
     conversion
    0.08
    转æį¢
    0.08
    åĨħéĥ¨
    0.08
    Conversion
    0.08
    è½īæıĽ
    0.08
    _conversion
    0.08
    FromClass
    0.08
     shift
    0.08
    _ratio
    0.08
    Activations Density 0.149%

    No Known Activations