© 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. 30246
    Prev
    Next
    INDEX
    Explanations

    need to

    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
    udeau
    -0.09
    quo
    -0.09
    öd
    -0.08
     prematurely
    -0.08
     getro
    -0.07
     demais
    -0.07
    ÑĢек
    -0.07
    éf
    -0.07
    -0.07
    ç»ļ
    -0.07
    POSITIVE LOGITS
     full
    0.08
    emos
    0.07
    ä¸įèĥ½æľī
    0.07
    brug
    0.06
     something
    0.06
     a
    0.06
    以æ±Ĥ
    0.06
    ¤
    0.06
    eppe
    0.06
     лÑĥÑĩÑĪего
    0.06
    Activations Density 0.009%

    No Known Activations