© 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. 54567
    Prev
    Next
    INDEX
    Explanations

    speed comparisons

    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
    éĤ£ä¹Ī容æĺĵ
    -0.10
    é¹ij
    -0.10
    æĶĴ
    -0.09
    çĬĦ
    -0.09
    å·²ä¹ħ
    -0.09
    çݯåį«
    -0.09
    ders
    -0.08
    ANTE
    -0.08
    coder
    -0.08
    bigint
    -0.08
    POSITIVE LOGITS
    å¥
    0.10
    /he
    0.09
    å®ŀæĥł
    0.09
    æī¼
    0.09
    èļĢ
    0.08
    éĢı
    0.08
    æķıéĶIJ
    0.08
    oon
    0.08
    åı£åı·
    0.08
    梯
    0.08
    Activations Density 0.085%

    No Known Activations