© 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. 47533
    Prev
    Next
    INDEX
    Explanations

    peptide, 's, inity, aging, acnes

    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
    ondre
    -0.08
    á»ijng
    -0.08
    çľĭå¾Ĺ
    -0.08
    aname
    -0.08
    iless
    -0.07
    bruch
    -0.07
    ·¸
    -0.07
    ardini
    -0.07
    室åĨħ空æ°Ķ
    -0.07
    adang
    -0.07
    POSITIVE LOGITS
     timeframe
    0.08
     timeline
    0.07
    ...
    0.07
     <<-
    0.07
    ite
    0.07
    ì²Ļ
    0.07
    ijľ
    0.07
     framework
    0.06
    æľīåħ³è§Ħå®ļ
    0.06
    lect
    0.06
    Activations Density 1.402%

    No Known Activations