© 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. 51450
    Prev
    Next
    INDEX
    Explanations

    wood and wood types

    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«©
    -0.09
    åIJ¬å¾Ĺ
    -0.09
    åı¯çĪ±
    -0.09
    å·¥ä½ľäººåijĺ
    -0.08
    appen
    -0.08
     Pry
    -0.08
    åĪ°è´¦
    -0.08
    íĪ¬
    -0.08
    åı¯ä¿¡
    -0.08
    éĶ¡
    -0.08
    POSITIVE LOGITS
    lemn
    0.12
     Dorm
    0.10
    çĸ¤
    0.10
    wood
    0.10
    WOOD
    0.10
    æĪĹ
    0.10
    èĪĨ
    0.10
    æľ¨
    0.10
    _FLUSH
    0.09
    chl
    0.09
    Activations Density 0.074%

    No Known Activations