© 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. 6336
    Prev
    Next
    INDEX
    Explanations

    interview

    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
    ocha
    -0.08
    讳
    -0.08
    åĭĥåĭĥ
    -0.08
    ä¸įåıĺ
    -0.08
    alk
    -0.08
     havoc
    -0.08
    æ´ĹèĦ¸
    -0.07
    LAB
    -0.07
    ifest
    -0.07
    bring
    -0.07
    POSITIVE LOGITS
    ê°Ŀ
    0.10
    çĽį
    0.10
    绶
    0.10
    ç¾Ķ
    0.10
    æĭ©
    0.09
    åİ®
    0.09
    è¾ĭ
    0.09
    ãĥıãĤ¤
    0.09
    è¿¢
    0.09
    æĬī
    0.08
    Activations Density 0.016%

    No Known Activations