© 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. 55053
    Prev
    Next
    INDEX
    Explanations

    famous animals named

    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
    麻çĹ¹
    -0.10
    -prof
    -0.09
    æĶ«
    -0.09
    stry
    -0.09
    leans
    -0.09
    讳
    -0.08
    ulan
    -0.08
    á»ĭch
    -0.08
    姻
    -0.08
     carr
    -0.08
    POSITIVE LOGITS
     mascot
    0.13
    åı¯çĪ±çļĦ
    0.12
    èIJ½æĪ·
    0.11
    ä¸Ĭå²Ĺ
    0.11
    亲åĪĩ
    0.11
     masc
    0.10
    活泼
    0.10
    £¼
    0.10
    形象
    0.09
    é²ľæ´»
    0.09
    Activations Density 0.122%

    No Known Activations