© 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. 53768
    Prev
    Next
    INDEX
    Explanations

    Indian River

    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
    è·Ľ
    -0.10
    å®ŀåĬĽ
    -0.09
    è¾īçħĮ
    -0.09
     cá»Ļng
    -0.09
    åįĥä¸ĩ
    -0.09
    åĶ§
    -0.09
    å©
    -0.09
    ä¸įèµ·
    -0.09
    é»ij马
    -0.09
    UnitOfWork
    -0.09
    POSITIVE LOGITS
    ¹
    0.09
    lake
    0.09
    stown
    0.09
    ish
    0.08
    ery
    0.08
    bow
    0.08
    ity
    0.08
    pak
    0.08
    £
    0.08
    zelf
    0.08
    Activations Density 0.013%

    No Known Activations