© 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. 53449
    Prev
    Next
    INDEX
    Explanations

    scheduled for the future

    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±ĭéĩĮ
    -0.10
    躺çĿĢ
    -0.10
    æݥ触åĪ°
    -0.09
    	TokenName
    -0.09
    æŃ£å½ĵ
    -0.09
     mũ
    -0.09
    åĿĹ
    -0.09
    ä¸ĢåĿĹ
    -0.09
    ä¸Ģéģĵ
    -0.09
    认è¯ĨåĪ°
    -0.09
    POSITIVE LOGITS
    iously
    0.12
    计åĪĴ
    0.11
    æ¯ģ
    0.10
    å°Ĩäºİ
    0.10
     slated
    0.10
    é¢Ħ计
    0.10
     scheduled
    0.10
     upcoming
    0.09
    ums
    0.09
    imed
    0.08
    Activations Density 0.086%

    No Known Activations