© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17833
    Prev
    Next
    INDEX
    Explanations

    alignment, comparison, diffing

    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
    è¾IJ
    -0.08
    iant
    -0.07
     Manor
    -0.07
     conosco
    -0.07
    åĨķ
    -0.07
     safety
    -0.06
    å¼ĢéŨ
    -0.06
     AM
    -0.06
     dangerously
    -0.06
    %i
    -0.06
    POSITIVE LOGITS
     alignment
    0.08
     Alignment
    0.08
    åĩºå¢ĥ
    0.08
    éĽĻæĸ¹
    0.08
    ALIGN
    0.08
    eaux
    0.08
     alignments
    0.08
    ä¸¤åĽ½
    0.08
    èĢĮéĻį
    0.08
     Align
    0.08
    Activations Density 0.015%

    No Known Activations