© 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. 10823
    Prev
    Next
    INDEX
    Explanations

    takes me a while

    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
    æĺİ天
    -0.10
    让人
    -0.10
    ÑĦе
    -0.10
    èĶļ
    -0.10
    è¶ģ
    -0.10
     пÑĢогн
    -0.09
    è®©æĽ´å¤ļ
    -0.09
    让
    -0.09
    大家ä¸Ģèµ·
    -0.09
    åħ¸ç¤¼
    -0.09
    POSITIVE LOGITS
    ä¸Ģ段æŶéĹ´
    0.10
    èī¯å¿ĥ
    0.09
    å¤ļå°ij
    0.09
    izzo
    0.09
     awhile
    0.09
    Atl
    0.08
    çĪ»
    0.08
    /vue
    0.08
    ä¸ĢçĶŁ
    0.08
     liking
    0.08
    Activations Density 0.009%

    No Known Activations