© 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. 17970
    Prev
    Next
    INDEX
    Explanations

    comments date

    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
     dob
    -0.07
     cur
    -0.07
     col
    -0.06
    anner
    -0.06
    çĥ¬
    -0.06
    ấp
    -0.06
    erna
    -0.06
    artz
    -0.06
    è·Įå®ķ
    -0.06
    à¹Īาà¸ĩ
    -0.06
    POSITIVE LOGITS
    izz
    0.08
    iT
    0.08
    ugd
    0.08
    reis
    0.07
    æĬĢæľ¯åĬĽéĩı
    0.07
    亡çģµ
    0.07
    FirstResponder
    0.07
     privilegi
    0.07
    illah
    0.07
    liz
    0.07
    Activations Density 0.283%

    No Known Activations