© 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. 58431
    Prev
    Next
    INDEX
    Explanations

    trick or tricks

    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
    estig
    -0.09
    WebpackPlugin
    -0.09
    欲滴
    -0.09
    isikan
    -0.09
    heu
    -0.08
    믹
    -0.08
     vét
    -0.08
    VERAGE
    -0.08
    IZE
    -0.08
    ational
    -0.08
    POSITIVE LOGITS
    ingly
    0.09
    ery
    0.09
    iness
    0.08
    ness
    0.08
    éĩįéĩį
    0.08
    åľ¨äºİ
    0.08
    éĩįéĩįçļĦ
    0.08
    imonial
    0.08
    åĦ¿çļĦ
    0.07
    полÑĥ
    0.07
    Activations Density 0.036%

    No Known Activations