© 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. 56233
    Prev
    Next
    INDEX
    Explanations

    ports and iptables

    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
    æݺ
    -0.10
    ä¸ĵåįĸ
    -0.10
    ç¸
    -0.10
    漪
    -0.09
    缩
    -0.09
    第ä¸ī代
    -0.09
    继æī¿
    -0.09
    诬
    -0.09
    çĮ¢
    -0.09
    èŀįåħ¥
    -0.08
    POSITIVE LOGITS
    çļĦèĥĮåIJİ
    0.09
    æľīæĿ¡ä»¶
    0.08
    对å¤ĸå¼ĢæĶ¾
    0.08
    anguages
    0.08
    çł
    0.08
    æī«
    0.08
    wing
    0.08
    é£İ
    0.08
    宽æĿ¾
    0.08
    èģĭ
    0.08
    Activations Density 0.151%

    No Known Activations