© 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. 56076
    Prev
    Next
    INDEX
    Explanations

    code blocks and strings

    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
    ooth
    -0.09
    anke
    -0.08
     detriment
    -0.07
    øv
    -0.07
    ween
    -0.07
    ÑĢÑĤа
    -0.07
    ekh
    -0.07
    éĽ¾éľ¾
    -0.07
    ÄĽk
    -0.07
     Goldberg
    -0.07
    POSITIVE LOGITS
    èĩªçĦ¶ç§ijåѦ
    0.08
    elix
    0.07
    ulumi
    0.07
    imiters
    0.07
    orne
    0.06
     languages
    0.06
     materials
    0.06
    submit
    0.06
    å¦Ĥä½ķåģļ
    0.06
    ixel
    0.06
    Activations Density 0.003%

    No Known Activations