© 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. 7082
    Prev
    Next
    INDEX
    Explanations

    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
    à¸Ńà¸ļ
    -0.09
    è¯ħ
    -0.09
    wij
    -0.09
    æīĭä¸Ń
    -0.09
    quine
    -0.09
    åĴĴ
    -0.09
     Ung
    -0.09
    æĻ®
    -0.09
    å·¥
    -0.09
     pall
    -0.09
    POSITIVE LOGITS
    åłµ
    0.10
    åłµå¡ŀ
    0.10
    çĩĶ
    0.10
    éĺ²çģ«
    0.09
    æĬµæĮ¡
    0.09
    æµģãĤĮ
    0.09
    å¾ĢæĿ¥
    0.09
    çIJĨè´¢
    0.09
    æķĻçłĶ
    0.08
    æĻļ
    0.08
    Activations Density 0.066%

    No Known Activations