© 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. 6676
    Prev
    Next
    INDEX
    Explanations

    assign/assigned/assignments

    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
    -0.11
    çĺ¾
    -0.11
    ened
    -0.10
    è¡·
    -0.10
    ész
    -0.10
    strap
    -0.10
    istics
    -0.10
    izer
    -0.09
    ousel
    -0.09
    ìĬ¨
    -0.09
    POSITIVE LOGITS
    ments
    0.15
    OrUpdate
    0.10
    åĴIJ
    0.10
    侧ç»ĵæŀĦæĢ§
    0.09
    IGNED
    0.09
    ned
    0.09
    æĪijåİ»
    0.09
    aturas
    0.09
    æĸ¼æĺ¯
    0.09
    ester
    0.09
    Activations Density 0.017%

    No Known Activations