© 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. 55871
    Prev
    Next
    INDEX
    Explanations

    not getting or would have

    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
    ampo
    -0.10
    åijĬè¯ī
    -0.10
    æĢİä¹Īåģļ
    -0.09
    å¯Łçľĭ
    -0.08
    æ¹ĺ
    -0.08
    ä¸įäºĪ
    -0.08
    åı¯ä¸įæĺ¯
    -0.08
    æĨ
    -0.08
    æĪijä¸Ģ缴
    -0.08
    CPF
    -0.08
    POSITIVE LOGITS
    æĶ¶åĪ°
    0.17
    å¾ĹåĪ°
    0.17
    èİ·å¾Ĺ
    0.17
    æĶ¶èİ·
    0.17
     receive
    0.15
    æĶ¶åĪ°äºĨ
    0.15
    çį²å¾Ĺ
    0.15
     полÑĥÑĩил
    0.14
    èİ·å¾ĹäºĨ
    0.14
    å¾ĹåĪ°äºĨ
    0.14
    Activations Density 0.141%

    No Known Activations