© 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. 24541
    Prev
    Next
    INDEX
    Explanations

    software license terms

    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
    elier
    -0.08
    _SLEEP
    -0.07
    äºĨ解ä¼ģä¸ļ
    -0.07
    å§ĵ
    -0.07
    åݻ年çļĦ
    -0.07
    обе
    -0.07
    ä¸įåıij
    -0.07
    eliers
    -0.06
    detach
    -0.06
    _foreign
    -0.06
    POSITIVE LOGITS
    egg
    0.07
    ixo
    0.07
    uny
    0.07
    سÙĪÙĨ
    0.07
    çĦ¶
    0.06
     loin
    0.06
    ForResult
    0.06
    suite
    0.06
    rage
    0.06
     echoing
    0.06
    Activations Density 0.381%

    No Known Activations