© 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. 6797
    Prev
    Next
    INDEX
    Explanations

    park

    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
    箧
    -0.09
    宿èĪį
    -0.09
    糯
    -0.09
    ÙĬاÙĨ
    -0.09
    éķ¿ä¸īè§Ĵ
    -0.09
    客æłĪ
    -0.08
    æĶ¶ç¼©
    -0.08
    lasses
    -0.08
     farmhouse
    -0.08
     Dorm
    -0.08
    POSITIVE LOGITS
    åħ¬åĽŃ
    0.20
    åħ¬åľĴ
    0.16
     park
    0.16
     parks
    0.14
    åħ¬åħ±
    0.12
     Parks
    0.12
    èįīåĿª
    0.11
    park
    0.11
     Park
    0.10
    /Public
    0.10
    Activations Density 0.104%

    No Known Activations