© 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. 17145
    Prev
    Next
    INDEX
    Explanations

    every owner of a

    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
    ä¸Ģæŀ¶
    -0.10
    ROME
    -0.10
    ä¸Ģèīĺ
    -0.10
    ä¿ĿèįIJ
    -0.09
    ç½Ĺ马
    -0.09
    èį¯åºĹ
    -0.08
    çķĪ
    -0.08
    ÙĦاÙĦ
    -0.08
    é¥Ńèıľ
    -0.08
     Loren
    -0.08
    POSITIVE LOGITS
    åħ±äº§åħļåijĺ
    0.09
    åıijçĥ§
    0.09
    åħ³å¿ĥ
    0.09
    à¸Ĭาว
    0.09
    èĢķèĢĺ
    0.09
    çĤİ
    0.08
    çĦ¦æĢ¥
    0.08
    UA
    0.08
    é¬ĵ
    0.08
    åŁºçĿ£å¾Ĵ
    0.08
    Activations Density 0.151%

    No Known Activations