© 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. 10532
    Prev
    Next
    INDEX
    Explanations

    description following

    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
    olin
    -0.10
    enticate
    -0.10
    æıIJéĹ®èĢħ
    -0.08
    ãĥ¼ãĥĹ
    -0.08
    :not
    -0.08
    ãĥ¼ãĤº
    -0.08
    çĬģ
    -0.08
    ÙĨÛĮÙĨ
    -0.07
    athers
    -0.07
    é§Ħ
    -0.07
    POSITIVE LOGITS
    OMEM
    0.07
    ãĢģ
    0.06
    erras
    0.06
    تÙĬÙĨ
    0.06
    缮æłĩåĴĮ
    0.06
    uel
    0.06
    о
    0.06
    RYPTO
    0.06
    acl
    0.06
    ihan
    0.06
    Activations Density 0.004%

    No Known Activations