© 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. 1103
    Prev
    Next
    INDEX
    Explanations

    conjunctions and transitional phrases

    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
    arez
    -0.08
    ajari
    -0.07
    бÑĥ
    -0.07
    ãģĻãĤĭãģ®ãģĭ
    -0.07
    :hidden
    -0.07
    iso
    -0.07
    isión
    -0.07
    ද
    -0.07
    çļĦè·¯ä¸Ĭ
    -0.07
    جار
    -0.07
    POSITIVE LOGITS
    inte
    0.07
    çĶ
    0.06
    åı¯
    0.06
    νή
    0.06
    龸
    0.06
    诺
    0.06
    çIJĨåºĶ
    0.06
    /single
    0.06
    çIJĨ论ä¸Ĭ
    0.06
    åºı
    0.06
    Activations Density 0.030%

    No Known Activations