© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9603
    Prev
    Next
    INDEX
    Explanations

    cell wall components structure

    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
    ä½¥
    -0.10
    çľŃ
    -0.09
    ç¹ģèį£
    -0.09
    åĢ¾åIJij
    -0.08
    æĪĺçģ«
    -0.08
     adj
    -0.08
    åŁ¹åħ»
    -0.08
    _OWNER
    -0.08
    æµĭ
    -0.08
    æĤ¨çļĦåŃ©åŃIJ
    -0.08
    POSITIVE LOGITS
    被æīĵ
    0.10
    éŀŃ
    0.10
    æµij
    0.10
    澤
    0.10
    icals
    0.09
    awei
    0.09
    _ABC
    0.09
    ICLES
    0.09
    ackers
    0.09
    éĿŀ常éĩįè¦ģ
    0.09
    Activations Density 0.415%

    No Known Activations