© 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. 57290
    Prev
    Next
    INDEX
    Explanations

    variable assignment and algebraic 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
    çĴĢ
    -0.09
    rix
    -0.09
    RIX
    -0.08
    osti
    -0.08
    PARSE
    -0.07
    为çĪ±
    -0.07
     chancellor
    -0.07
    AFF
    -0.07
    _AES
    -0.07
    pere
    -0.07
    POSITIVE LOGITS
    endere
    0.07
    mej
    0.07
    icy
    0.07
    icone
    0.07
    ambre
    0.07
    impl
    0.06
    èĥ¶
    0.06
    å¿ĺ
    0.06
    ullet
    0.06
    ä¸īå²ģ
    0.06
    Activations Density 0.016%

    No Known Activations