© 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. 49020
    Prev
    Next
    INDEX
    Explanations

    concluding 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
    arl
    -0.10
    åĩłä¹İ没æľī
    -0.09
    endale
    -0.09
    ä½Ĩä»İ
    -0.09
    绿
    -0.09
    legg
    -0.08
    éĹªåħī
    -0.08
    åĴĸ
    -0.08
    riend
    -0.08
    =sys
    -0.08
    POSITIVE LOGITS
    ä¸Ģæĺ¯
    0.12
    è¦ģä¹Ī
    0.11
    åħ¶ä¸Ńä¹ĭä¸Ģ
    0.11
     nämlich
    0.11
     Nam
    0.10
    åĪĨåĪ«æĺ¯
    0.10
    Nam
    0.10
    åħĪæĺ¯
    0.10
    éĤ£å°±æĺ¯
    0.10
    :
    0.10
    Activations Density 0.277%

    No Known Activations