© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9630
    Prev
    Next
    INDEX
    Explanations

    neutrino

    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
    пÑĥÑģ
    -0.09
    mach
    -0.09
    ç©¿
    -0.09
    å°Ķæĸ¯
    -0.09
    ç©¿è¿ĩ
    -0.09
    á½¼
    -0.08
    çģ«çĥŃ
    -0.08
    ä¸Ģ楼
    -0.08
    éĶij
    -0.08
    ype
    -0.08
    POSITIVE LOGITS
    agination
    0.09
    æĮ¤
    0.09
     sealed
    0.09
    å¾Īéķ¿
    0.09
    icorn
    0.09
    滩
    0.08
    .sg
    0.08
    eten
    0.08
    å¿ĥæĦ¿
    0.08
    åĨľ
    0.08
    Activations Density 0.025%

    No Known Activations