© 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. 29002
    Prev
    Next
    INDEX
    Explanations

    doping, drug, steroid, war, vulkan, symbiont

    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
    P
    -0.06
    M
    -0.06
    3
    -0.06
     P
    -0.05
    éĹª
    -0.05
    åĢĴ
    -0.05
    æĺĤ
    -0.05
    .p
    -0.05
    lop
    -0.05
    POSITIVE LOGITS
    .nodeType
    0.09
    ắ
    0.09
    ä¸ĩäºĭ
    0.09
    éĸ
    0.08
    ronym
    0.08
    Ắ
    0.08
    ikiran
    0.08
    .indent
    0.08
    ordu
    0.08
    ίκη
    0.08
    Activations Density 0.116%

    No Known Activations