© 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. 62561
    Prev
    Next
    INDEX
    Explanations

    make and made

    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
    odom
    -0.10
    åı¦æľī
    -0.10
    å±ģèĤ¡
    -0.09
    æĸ°çĶŁ
    -0.09
    é¢IJ
    -0.09
    tti
    -0.09
    æ·ĭ
    -0.09
    çĹĪ
    -0.09
    ÐĿЫ
    -0.09
    åĸı
    -0.08
    POSITIVE LOGITS
    éĢĤ度
    0.10
    è§Ĭ
    0.09
    é£ŀè·ĥ
    0.09
    åħ§éĥ¨
    0.09
    åĨħéĥ¨
    0.09
    çĽį
    0.09
    ä½ĵåĪ¶æĶ¹éĿ©
    0.08
     даж
    0.08
    å½°
    0.08
    两次
    0.08
    Activations Density 0.081%

    No Known Activations