© 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. 5469
    Prev
    Next
    INDEX
    Explanations

    new beginnings, future, life chapters

    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
    aret
    -0.09
    è¿Ļä½į
    -0.09
    ATTR
    -0.09
    adro
    -0.09
    çĪĨ
    -0.09
    åĮºåĪĨ
    -0.08
    urm
    -0.08
    culo
    -0.08
    holes
    -0.08
    è¦ģ害
    -0.08
    POSITIVE LOGITS
    lags
    0.10
    bildung
    0.09
    è°İè¨Ģ
    0.09
     trag
    0.09
    è°Īè¯Ŀ
    0.09
    пеÑĩ
    0.09
    滥
    0.08
    çļĦä¸ĢéĿ¢
    0.08
    æĿµ
    0.08
    好çļĦ
    0.08
    Activations Density 0.034%

    No Known Activations