© 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. 53803
    Prev
    Next
    INDEX
    Explanations

    worth the

    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
    ä¹ĭç¾İ
    -0.09
    æ¶īåıĬåĪ°
    -0.09
     deser
    -0.08
    稼
    -0.08
    ä¸ĩäºĭ
    -0.08
    缸å½ĵäºİ
    -0.08
    æįŀ
    -0.08
    CSR
    -0.08
    avy
    -0.08
    ãĥ£
    -0.08
    POSITIVE LOGITS
    è¹Ī
    0.09
    麻çĥ¦
    0.09
     effort
    0.09
    çħ
    0.08
     ÑĥÑģили
    0.08
    çĽ¼
    0.08
    æĨĤ
    0.08
    NotExist
    0.08
    åIJ«
    0.08
    é¢ĵ
    0.08
    Activations Density 0.009%

    No Known Activations