© 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. 63196
    Prev
    Next
    INDEX
    Explanations

    origins, roots, or legacy

    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
    æ´½
    -0.10
    olk
    -0.09
    ä¹ĭä¸ĭ
    -0.09
    çݰ代åĮĸ
    -0.09
    æݪ
    -0.09
    èĶ«
    -0.09
    scheme
    -0.09
    çļĦ人çĶŁ
    -0.09
    æĻļå¹´
    -0.09
    æijħ
    -0.09
    POSITIVE LOGITS
     origins
    0.15
     origin
    0.12
     heritage
    0.12
    åĩºå¤Ħ
    0.11
    åĩºèº«
    0.11
    åĪĿè¡·
    0.11
    èµ·æºIJ
    0.11
     roots
    0.11
    æł¹æºIJ
    0.11
     Origins
    0.10
    Activations Density 0.039%

    No Known Activations