© 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. 55362
    Prev
    Next
    INDEX
    Explanations

    itself / its own

    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
    åħ¶
    -0.09
    ighted
    -0.09
    utow
    -0.09
    æľŁåĨħ
    -0.09
    haps
    -0.08
    ä»ĸ们
    -0.08
    кÑĢо
    -0.08
    hart
    -0.08
    ÑĢег
    -0.08
    ä»ĸ人
    -0.08
    POSITIVE LOGITS
    -même
    0.14
    zelf
    0.13
    çļĦ人çī©
    0.12
    çļĦä¸ĢäºĽ
    0.11
    åįģ足
    0.10
     own
    0.10
    /her
    0.10
    çļĦ羣å®ŀæĢ§
    0.09
    æ²Ľ
    0.09
     próprio
    0.09
    Activations Density 0.056%

    No Known Activations