© 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. 56198
    Prev
    Next
    INDEX
    Explanations

    options or properties

    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
    好æ±ī
    -0.07
    berger
    -0.07
    /tty
    -0.07
    ÑĢее
    -0.07
    Cadastro
    -0.07
    åĩºå¸ŃäºĨ
    -0.07
    жо
    -0.07
    <|box_end|>
    -0.07
    isArray
    -0.07
    ENTA
    -0.07
    POSITIVE LOGITS
    ?:
    0.07
     optionally
    0.07
    |
    0.06
     efficiently
    0.06
    hib
    0.06
    å¹½é»ĺ
    0.06
    issy
    0.06
    å°ļ
    0.06
    )?
    0.06
    irian
    0.06
    Activations Density 0.069%

    No Known Activations