© 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. 30113
    Prev
    Next
    INDEX
    Explanations

    company, trading, shipping, production, wholesale

    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
    ystal
    -0.09
     FD
    -0.09
    秦
    -0.09
    xfd
    -0.09
    FD
    -0.09
    (fd
    -0.09
     misses
    -0.09
     corporate
    -0.08
    adt
    -0.08
     Gly
    -0.08
    POSITIVE LOGITS
    çİ©åħ·
    0.10
    æ§Ł
    0.09
    ieten
    0.09
    å®ŀåĬĽ
    0.09
    è´¨éĩıå®īåħ¨
    0.08
     Unblock
    0.08
    ribly
    0.08
     Notebook
    0.08
    森æŀĹåħ¬åĽŃ
    0.08
    ç»ĵæŀĦè°ĥæķ´
    0.08
    Activations Density 0.072%

    No Known Activations