© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51524
    Prev
    Next
    INDEX
    Explanations

    sharp and acute descriptions

    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
    defs
    -0.10
    æĶ¯æŁ±
    -0.09
    spo
    -0.09
    arı
    -0.09
    解æĶ¾
    -0.08
    finally
    -0.08
    mers
    -0.08
    æ½¢
    -0.08
    ä¸Ģè¶Ł
    -0.08
    urations
    -0.08
    POSITIVE LOGITS
    éĶIJ
    0.15
    -eyed
    0.13
    æĢĨ
    0.12
    å°ĸ
    0.12
     sharpen
    0.11
     sharp
    0.10
    çĬĢ
    0.10
     sharper
    0.10
    Sharp
    0.10
     sharply
    0.10
    Activations Density 0.041%

    No Known Activations