© 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. 61257
    Prev
    Next
    INDEX
    Explanations

    valid/invalid states

    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
    ums
    -0.07
    以éĢĤåºĶ
    -0.06
     modern
    -0.06
     rum
    -0.06
    åįĩ
    -0.06
    opian
    -0.06
    大湾åĮº
    -0.06
     chargé
    -0.06
    expects
    -0.06
     Rum
    -0.06
    POSITIVE LOGITS
    valid
    0.09
    arine
    0.09
     valid
    0.08
     invalid
    0.08
     validity
    0.08
    egner
    0.08
    (valid
    0.07
     Invalid
    0.07
    æ£ĢæŁ¥ç»ĵæŀľ
    0.07
    invalid
    0.07
    Activations Density 0.003%

    No Known Activations