© 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. 56744
    Prev
    Next
    INDEX
    Explanations

    squid or id

    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
    ubar
    -0.09
    å¾Ĥ
    -0.09
    ëĮĢë¡ľ
    -0.08
    æģ¨
    -0.08
    çģĮ
    -0.08
    æ¹ĥ
    -0.08
    ANI
    -0.08
    ioni
    -0.08
    bour
    -0.08
    agen
    -0.08
    POSITIVE LOGITS
    estre
    0.10
    æŶä¸į
    0.10
    acious
    0.09
    æ¥ł
    0.09
    ster
    0.08
    sters
    0.08
    .UserService
    0.08
     تÙħاÙħ
    0.08
    ertino
    0.08
    arto
    0.08
    Activations Density 0.003%

    No Known Activations