© 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. 20323
    Prev
    Next
    INDEX
    Explanations

    Episode number or pages

    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
    两èĢħ
    -0.09
     вообÑīе
    -0.09
     Wed
    -0.09
    å¯Ħ
    -0.08
    sing
    -0.08
    erer
    -0.08
    请çĤ¹åĩ»
    -0.08
    ulp
    -0.08
     ment
    -0.08
    æ¹Ľ
    -0.08
    POSITIVE LOGITS
    LOOP
    0.10
    ä½łä¼ļåıijçİ°
    0.09
    æ»Ķ
    0.09
    æĮĽ
    0.09
    ä¹ħä¹ħ
    0.08
    uates
    0.08
    æĪijå¿ĥéĩĮ
    0.08
    ç©¿è¡£
    0.08
    åİ»æī¾
    0.08
    è¶ĬæĿ¥è¶Ĭ
    0.08
    Activations Density 0.092%

    No Known Activations