© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22694
    Prev
    Next
    INDEX
    Explanations

    precisely constrain cosmological parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    横
    -0.08
    éĴľ
    -0.08
    éħ·
    -0.08
    rens
    -0.08
    imity
    -0.08
    ë¡Ŀ
    -0.08
    ä»Ģ麽
    -0.08
    isen
    -0.08
    inch
    -0.08
    _weather
    -0.08
    POSITIVE LOGITS
    ç¼¥
    0.11
    xis
    0.11
    egin
    0.11
    饼
    0.10
    egl
    0.10
    eg
    0.10
    ÑıÑīиÑħ
    0.09
    agu
    0.09
    EGIN
    0.09
    严å¯Ĩ
    0.09
    Activations Density 0.043%

    No Known Activations