© 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. 33382
    Prev
    Next
    INDEX
    Explanations

    what to express

    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
     anonymous
    -0.08
     MAD
    -0.08
    棱
    -0.08
    çĿ½
    -0.08
     backed
    -0.08
     Vander
    -0.08
    çĸı
    -0.08
     Mad
    -0.08
    ç¨
    -0.07
    umm
    -0.07
    POSITIVE LOGITS
    个åĪ«
    0.15
    èĢĮæĺ¯
    0.13
     nor
    0.12
    æĪĸåħ¶ä»ĸ
    0.11
    éĿŀè¦ģ
    0.11
    次è¦ģ
    0.11
    åħ·ä½ĵåĨħ容
    0.10
    æľªå©ļ
    0.10
    èĩĨ
    0.10
    æŁIJä¸Ģ
    0.10
    Activations Density 0.109%

    No Known Activations