© 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. 48901
    Prev
    Next
    INDEX
    Explanations

    thermosetting adhesives or laminates

    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
     Spicer
    -0.09
    æŀ¨
    -0.09
    ilt
    -0.08
    åĸĦ
    -0.08
    SW
    -0.08
    opic
    -0.08
    èĩªå·±åĸľæ¬¢
    -0.08
    .rep
    -0.08
     Sparks
    -0.08
    akis
    -0.08
    POSITIVE LOGITS
     Arnold
    0.10
    åŁºè¾ħ
    0.09
    å¸ľ
    0.09
    线ä¸Ĭ线ä¸ĭ
    0.09
    ä¸Ĭä¸ĭ
    0.09
    PET
    0.09
    å°ijä¸įäºĨ
    0.09
    æ³ķåĪ¶
    0.09
    æĦ¦
    0.09
    DM
    0.09
    Activations Density 0.115%

    No Known Activations