© 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. 49043
    Prev
    Next
    INDEX
    Explanations

    download, pet, Framework, label

    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
    -0.07
     (
    -0.07
    ...
    -0.06
     a
    -0.06
    çŃīåħ¶ä»ĸ
    -0.06
     ins
    -0.06
     New
    -0.05
     ...
    -0.05
    odal
    -0.05
     B
    -0.05
    POSITIVE LOGITS
    éal
    0.08
    ä¸įèĥ½åIJĥ
    0.08
    åĢĴä¸ĭ
    0.08
    ombre
    0.08
    åºĥåijĬãģ¯
    0.08
    .generated
    0.08
    ød
    0.08
    reté
    0.08
    andid
    0.08
    awas
    0.08
    Activations Density 0.004%

    No Known Activations