© 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. 63550
    Prev
    Next
    INDEX
    Explanations

    non-

    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
    å¸Ń
    -0.11
    常年
    -0.11
    颧
    -0.11
    ittel
    -0.10
    errno
    -0.10
    æ¯ħ
    -0.10
    åħ¶ä¸Ńä¸Ģ个
    -0.09
    æīįç®Ĺ
    -0.09
    .codes
    -0.09
    æĥ³ä¸įåĪ°
    -0.09
    POSITIVE LOGITS
    èı½
    0.11
    iros
    0.10
    åĪ°æĿ¥
    0.09
    è¾¾æłĩ
    0.08
    chal
    0.08
    æĦıä¹īä¸Ĭ
    0.08
    -existent
    0.08
    дв
    0.08
    illions
    0.08
    åľ»
    0.08
    Activations Density 0.028%

    No Known Activations