© 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. 3265
    Prev
    Next
    INDEX
    Explanations

    next followed by a word or punctuation

    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
    åIJĦæł·
    -0.09
    ÑģÑĮ
    -0.09
    nee
    -0.09
    ycl
    -0.09
    å¾Īæ·±
    -0.09
    æĪĸå¤ļ
    -0.08
    trl
    -0.08
    ä¸İæĹ¶ä¿±è¿Ľ
    -0.08
    sports
    -0.08
    animated
    -0.08
    POSITIVE LOGITS
    rok
    0.11
    ä¸Ģ个éĹ®é¢ĺ
    0.10
     next
    0.09
    NEXT
    0.09
    -next
    0.09
     NEXT
    0.09
    next
    0.09
     Next
    0.09
    Next
    0.09
    ferred
    0.08
    Activations Density 0.034%

    No Known Activations