© 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. 5111
    Prev
    Next
    INDEX
    Explanations

    pharmacy and pharmacist

    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
    ance
    -0.09
    ances
    -0.09
    -0.09
    åĥı个
    -0.09
    AFP
    -0.09
    erview
    -0.09
    æĸ°éĹ»åıijå¸ĥ
    -0.09
     amp
    -0.08
    è¾ĥ好
    -0.08
    pton
    -0.08
    POSITIVE LOGITS
    æĪŁ
    0.09
    eros
    0.09
    éĭª
    0.09
    aceut
    0.09
    ony
    0.08
     breathable
    0.08
    ellas
    0.08
    éŨåı£
    0.08
    ä¸Ģå¤Ħ
    0.08
    rupt
    0.08
    Activations Density 0.008%

    No Known Activations