© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51878
    Prev
    Next
    INDEX
    Explanations

    I am looking for

    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
    å¾Īå¿«
    -0.10
    è°
    -0.09
    好åIJ§
    -0.09
    éļ¾æĢª
    -0.09
    æīįè¡Į
    -0.08
     pairs
    -0.08
    ird
    -0.08
    åĥŃ
    -0.08
    以åħį
    -0.08
    çĨ
    -0.08
    POSITIVE LOGITS
    éĹ®é¢ĺæĺ¯
    0.13
    ãĤĭãģ®ãģ¯
    0.11
    çī¹çĤ¹æĺ¯
    0.11
    åľĨå½¢
    0.10
    åħ³éĶ®æĺ¯
    0.10
    æľĢæľī
    0.10
     Tender
    0.09
    åİŁåĽłæĺ¯
    0.09
    sched
    0.09
    ãģĻãĤĭãģ®ãģ¯
    0.09
    Activations Density 0.153%

    No Known Activations