© 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. 58001
    Prev
    Next
    INDEX
    Explanations

    inevitable or problems

    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
    _PRIMARY
    -0.09
    满èĦ¸
    -0.09
    满足
    -0.09
    rew
    -0.09
    å±ij
    -0.09
    æŃ£å®Ĺ
    -0.09
    ä¹ħ
    -0.08
    æ··åĩĿ
    -0.08
    äºĨä¸Ģåı¥
    -0.08
    reo
    -0.08
    POSITIVE LOGITS
    ä¸įåı¯éģ¿åħį
    0.17
    éļ¾åħį
    0.16
    æĢ»ä¼ļ
    0.14
    éĥ½ä¼ļæľī
    0.13
    ä¸įåħį
    0.11
    ãģ¯ãģĤãĤĭ
    0.11
    ä»»ä½ķä¸Ģ个
    0.10
    åĿ¦
    0.10
    èµ·ä¼ı
    0.10
    ä¸įåı¯èĥ½
    0.10
    Activations Density 0.068%

    No Known Activations