© 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. 33108
    Prev
    Next
    INDEX
    Explanations

    'd like to

    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
    eeee
    -0.09
    ãĤĤãĤī
    -0.09
    ä½Ĩä¸įéĻIJäºİ
    -0.09
    ÑĥÑħ
    -0.08
    å¤ĸéĿ¢
    -0.08
    ä¸IJ
    -0.08
    ä»Ģä¹Īåij¢
    -0.08
    çľ¼è§Ĵ
    -0.08
    款项
    -0.08
    dB
    -0.08
    POSITIVE LOGITS
    roid
    0.11
    å·²ä¹ħçļĦ
    0.10
    acity
    0.09
    irect
    0.09
    iges
    0.09
    çĦ¶æĺ¯
    0.09
    imension
    0.09
    -contrib
    0.09
    irector
    0.09
    ownload
    0.09
    Activations Density 0.018%

    No Known Activations