© 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. 30172
    Prev
    Next
    INDEX
    Explanations

    of the

    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
    åĪ°æľĢåIJİ
    -0.09
    otel
    -0.09
    rag
    -0.09
    æľ¦
    -0.09
    èģĮ
    -0.09
    cape
    -0.08
    IFA
    -0.08
    ä¸Ģæ³¢
    -0.08
    _rg
    -0.08
    ä¸Ģä½į
    -0.08
    POSITIVE LOGITS
    æĶ¾å¿ĥ
    0.09
    å°ĸåı«
    0.09
    çĶ·äºº
    0.09
    赶
    0.08
     обÑĢаÑī
    0.08
    /fw
    0.08
    æıĨ
    0.08
    æı´
    0.08
    åī¯å¸Ĥéķ¿
    0.08
    .fail
    0.08
    Activations Density 0.101%

    No Known Activations