© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9214
    Prev
    Next
    INDEX
    Explanations

    never miss or pay

    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
    å§ij
    -0.11
    åĽ¢åľĨ
    -0.09
     obsc
    -0.09
    污
    -0.09
    /cop
    -0.09
    urdy
    -0.09
    èªī
    -0.08
    è°¯
    -0.08
    æĦļ
    -0.08
    èĪĴæľį
    -0.08
    POSITIVE LOGITS
    çľ¼çļ®
    0.10
    èIJ½åľ°
    0.09
    ãģ£
    0.09
    apesh
    0.09
    æĸ¹æĸ¹éĿ¢
    0.09
    çļĦæŃ¥ä¼IJ
    0.09
    çīµæĮĤ
    0.09
    åıĮçľ¼
    0.08
    åĩłçĻ¾
    0.08
    æĥ³åĪ°
    0.08
    Activations Density 0.044%

    No Known Activations