© 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. 53907
    Prev
    Next
    INDEX
    Explanations

    morphological variation, starvation, jar assay

    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¸Į
    -0.08
    à¸Ĺร
    -0.08
    è¿ĩ渡
    -0.08
    èĤĺ
    -0.08
    æ»ijéĽª
    -0.08
     brib
    -0.08
    èĤłèĥĥ
    -0.08
    çĬ¬
    -0.08
    ç¾Ĭ
    -0.08
    æIJ¶
    -0.08
    POSITIVE LOGITS
    èļĤ
    0.12
    èļľ
    0.12
    èĽ¹
    0.12
    èĻ«
    0.10
    èŀ¨
    0.10
    brook
    0.10
    èĿĹ
    0.10
    åı®
    0.10
    éļ¶
    0.10
    èĽĽ
    0.10
    Activations Density 0.590%

    No Known Activations