© 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. 4420
    Prev
    Next
    INDEX
    Explanations

    then followed by `to` or `then`

    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
    æѤæŶ
    -0.11
    äºĭåħĪ
    -0.11
    è¿ĻæŶ
    -0.11
    å±ĬæŶ
    -0.11
    thus
    -0.11
     пÑĢежде
    -0.10
    æĪijçİ°åľ¨
    -0.10
     thus
    -0.10
    åĪĿè¡·
    -0.10
    æѤæĻĤ
    -0.10
    POSITIVE LOGITS
     Ùħباشرة
    0.09
    åıĪ被
    0.09
    åĽŀæĿ¥
    0.09
    ãģ£ãģįãĤĬ
    0.09
    åħ¶ä»ĸçļĦ
    0.09
    åıĪ
    0.08
    Later
    0.08
    dob
    0.08
    ä¸Ģ声
    0.08
    æŃ¤åŁºç¡Ģä¸Ĭ
    0.08
    Activations Density 0.215%

    No Known Activations