© 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. 42158
    Prev
    Next
    INDEX
    Explanations

    purchase related words

    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
    éĢĻå¹¾
    -0.07
    yll
    -0.07
    feit
    -0.07
    ality
    -0.06
    ENCE
    -0.06
    å½ĵä¹ĭ
    -0.06
    ÄĻzy
    -0.06
    quettes
    -0.06
    irks
    -0.06
    burse
    -0.06
    POSITIVE LOGITS
    ¹
    0.08
    ħ
    0.08
    ellow
    0.07
    ering
    0.07
    ube
    0.07
    «
    0.07
    ott
    0.07
    ucha
    0.07
    afa
    0.07
    elter
    0.07
    Activations Density 0.001%

    No Known Activations