© 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. 16077
    Prev
    Next
    INDEX
    Explanations

    rounding and integral operations

    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
    大ä¸ī
    -0.08
    ä¸Ĭè·¯
    -0.08
    èĢĮ代ä¹ĭ
    -0.07
    ç½Ħ
    -0.07
     subsystem
    -0.07
    á»ĩp
    -0.07
    éĩij森
    -0.07
    uxt
    -0.07
    åľ¨å®ħ
    -0.07
    ANCES
    -0.07
    POSITIVE LOGITS
    edis
    0.08
    ilis
    0.07
    ä¸įå½Ĵ
    0.07
    ToInt
    0.07
    ÑĢоб
    0.07
    floor
    0.07
    åĢ¾åIJij
    0.07
    çĸ¤
    0.07
    éĺħ读åħ¨æĸĩ
    0.07
    ceil
    0.07
    Activations Density 0.010%

    No Known Activations