© 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. 8451
    Prev
    Next
    INDEX
    Explanations

    where, extent, appropriate, necessary, possible

    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
    çļĦæľīæķĪ
    -0.09
    sky
    -0.09
    ãģĿãĤĤãģĿãĤĤ
    -0.08
    æ·±åĪ»çļĦ
    -0.08
     Te
    -0.08
    åĪĴåĪĨ
    -0.08
    éĥ½æľīèĩªå·±
    -0.08
    tti
    -0.08
    Forgot
    -0.08
     Met
    -0.07
    POSITIVE LOGITS
    å°½éĩı
    0.18
    å°½åı¯èĥ½
    0.13
    å¿ħè¦ģ
    0.12
    æĥħåĨµä¸ĭ
    0.11
    æľīå¿ħè¦ģ
    0.10
    oad
    0.10
     möglich
    0.10
    rama
    0.10
     возможно
    0.09
    æĹłåı¯
    0.09
    Activations Density 0.029%

    No Known Activations