© 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. 44059
    Prev
    Next
    INDEX
    Explanations

    's followed by "all", "a", "the", "how", "what"

    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
    ä¸ĢæŶçļĦ
    -0.09
    غة
    -0.08
    asar
    -0.07
    usus
    -0.07
    tagen
    -0.07
    écr
    -0.07
    urso
    -0.07
     foregoing
    -0.07
    ropp
    -0.07
    ahoo
    -0.07
    POSITIVE LOGITS
    itting
    0.07
    омÑĥ
    0.07
    prising
    0.07
    å§Ĩæĸ¯
    0.07
    )):
    0.07
    AMA
    0.06
    $:
    0.06
    »:
    0.06
    __:
    0.06
    .):
    0.06
    Activations Density 0.109%

    No Known Activations