© 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. 60191
    Prev
    Next
    INDEX
    Explanations

    heartbreaking

    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
    çĶļèĩ³æľī
    -0.07
    sembler
    -0.07
    elib
    -0.07
    èo
    -0.07
    ration
    -0.07
    /tags
    -0.07
    顺å¿ĥ
    -0.06
     Estilo
    -0.06
    ä¼łä¸ĸ
    -0.06
    .Experimental
    -0.06
    POSITIVE LOGITS
    ä½ĨåıĪ
    0.24
    ä½ĨåIJĮæŶ
    0.21
    åIJĮæŶåıĪ
    0.21
     yet
    0.21
    åį´åıĪ
    0.20
    èĢĮåıĪ
    0.19
    yet
    0.18
    åıĪä¸į失
    0.16
    åį»åıĪ
    0.16
    ä½Ĩä»į
    0.16
    Activations Density 0.240%

    No Known Activations