© 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. 31643
    Prev
    Next
    INDEX
    Explanations

    Dolphin and dolphins

    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
    stellen
    -0.09
    lingen
    -0.09
    inee
    -0.09
    æĪIJåŀĭ
    -0.09
    头èĦij
    -0.09
    ly
    -0.09
    åı£è¢ĭ
    -0.08
     Äijông
    -0.08
    otec
    -0.08
     Lips
    -0.08
    POSITIVE LOGITS
    achu
    0.10
    æģĻ
    0.09
    ail
    0.09
     mát
    0.09
    enge
    0.08
    åıĭ们
    0.08
    åģĥ
    0.08
    åħ¶ä»ĸåĽ½å®¶
    0.08
    มà¸Ńà¸ĩ
    0.08
    arity
    0.08
    Activations Density 0.003%

    No Known Activations