© 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. 63699
    Prev
    Next
    INDEX
    Explanations

    links and code references

    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
    æ¸ł
    -0.09
    ãĥŃãĥ¼
    -0.09
     Aure
    -0.09
    ä¸Ģè´¯
    -0.09
    éĺµ
    -0.09
    è¾ħ
    -0.09
    æĺķ
    -0.09
    ÑĢеÑģÑĤ
    -0.09
    磶
    -0.09
     Nes
    -0.08
    POSITIVE LOGITS
    esome
    0.09
    è¿ĺæĥ³
    0.09
    éĩįéĩį
    0.08
    quat
    0.08
    ä¸įçĶĺ
    0.08
    çĶ¨åĬĽ
    0.08
    éĻĽ
    0.08
    宫廷
    0.08
    çİ©åħ·
    0.08
    产ä¸ļéĵ¾
    0.08
    Activations Density 0.059%

    No Known Activations