© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21572
    Prev
    Next
    INDEX
    Explanations

    -able, -ible, -ably suffixes

    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
    esh
    -0.11
    very
    -0.10
    å´ŀ
    -0.09
    æł¹æľ¬
    -0.09
    rab
    -0.08
    fer
    -0.08
    ä¸ĢçĽ´æ²¡æľī
    -0.08
     ho
    -0.08
    Inflater
    -0.08
    è¿ĺ好
    -0.08
    POSITIVE LOGITS
    ible
    0.11
    ibly
    0.10
    iable
    0.10
    éĶĻè¿ĩ
    0.10
    æĪĸå¤ļæĪĸå°ij
    0.09
    éģĹæ¼ı
    0.09
    ably
    0.09
    æ£
    0.09
    umper
    0.09
    owed
    0.09
    Activations Density 0.038%

    No Known Activations