© 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. 2096
    Prev
    Next
    INDEX
    Explanations

    performance improvement or optimization

    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
    ness
    -0.13
    å±ij
    -0.11
    inding
    -0.10
    åĦ¿
    -0.10
    ork
    -0.10
    iales
    -0.10
    inary
    -0.10
    lings
    -0.10
    ulence
    -0.10
    ships
    -0.09
    POSITIVE LOGITS
     quo
    0.10
    æѤåĪ»
    0.09
     Borough
    0.09
    åįģ足
    0.09
    legg
    0.09
    sing
    0.09
    æĶ¸
    0.09
    è¶Ĭ
    0.09
    ioned
    0.09
    åħħåĪĨä½ĵçİ°
    0.08
    Activations Density 0.031%

    No Known Activations