© 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. 57071
    Prev
    Next
    INDEX
    Explanations

    round and circular shapes

    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
    ocratic
    -0.10
    æŃª
    -0.09
    åİ¥
    -0.09
    éĽĦ
    -0.09
    æĻ®éĢļ人
    -0.08
     Kot
    -0.08
    èĺĸ
    -0.08
    illet
    -0.08
    è¡©
    -0.08
    æĮģãģ¡
    -0.08
    POSITIVE LOGITS
    rego
    0.09
    ity
    0.09
    ish
    0.09
    æݨèįIJéĺħ读
    0.09
    -ish
    0.09
    adia
    0.08
    çŃĽ
    0.08
    ITY
    0.08
     dia
    0.08
     pilgr
    0.08
    Activations Density 0.236%

    No Known Activations