© 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. 3223
    Prev
    Next
    INDEX
    Explanations

    parasite and symbiont interactions

    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£ģ
    -0.10
    æijĩ
    -0.09
    åĽ´å¢Ļ
    -0.09
    oug
    -0.09
     cps
    -0.09
    æIJĸ
    -0.09
    壬
    -0.09
     repost
    -0.09
    ä»ħä¾Ľ
    -0.09
    atorio
    -0.08
    POSITIVE LOGITS
    omap
    0.10
    å¿łè¯ļ
    0.10
    亲çĪ±
    0.09
    kee
    0.09
    ä¸ī代
    0.09
    æ·Ļ
    0.09
    /jav
    0.09
    代çIJĨ
    0.09
    _hosts
    0.09
    游泳
    0.08
    Activations Density 0.221%

    No Known Activations