© 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. 22339
    Prev
    Next
    INDEX
    Explanations

    finalists and finals

    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
    ening
    -0.13
    fully
    -0.10
    ifton
    -0.10
    iest
    -0.09
    UIS
    -0.09
    itra
    -0.09
    è¹Ĭ
    -0.09
    çĸĹæ³ķ
    -0.09
    ened
    -0.08
    oen
    -0.08
    POSITIVE LOGITS
    rush
    0.09
     ITE
    0.09
    ow
    0.09
    §
    0.09
    缮çļĦæĺ¯
    0.09
    xed
    0.09
    ogy
    0.09
    볬
    0.09
    æĮĪ
    0.09
    ê¸ī
    0.09
    Activations Density 0.020%

    No Known Activations