© 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. 47915
    Prev
    Next
    INDEX
    Explanations

    sorption, diffusion, absorbed, hydroscopic

    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
    åIJ¬å¾Ĺ
    -0.09
    å¼ij
    -0.09
    以èī²
    -0.09
    è¦Ĩ
    -0.08
    çĪĨçĤ¸
    -0.08
    èĻļå¼±
    -0.08
    èĬĤå¥ı
    -0.08
    çŁ¥éģĵäºĨ
    -0.08
    éĩĿ
    -0.08
    æĩĭ
    -0.08
    POSITIVE LOGITS
    湿度
    0.09
    æĿŀ
    0.09
    ä¿Ĺ称
    0.09
    饱
    0.08
    å°±ä¸įèĥ½
    0.08
    ARA
    0.08
    åĢ¼å®Ī
    0.08
     MOZ
    0.08
    arden
    0.08
    .getCount
    0.08
    Activations Density 0.176%

    No Known Activations