© 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. 10585
    Prev
    Next
    INDEX
    Explanations

    between, than, as, too, over, from

    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
    _Adjust
    -0.10
    ocrats
    -0.10
    velope
    -0.09
    atile
    -0.09
    çĶ¨åĬĽ
    -0.09
     peanut
    -0.09
    çĩ§
    -0.09
    gings
    -0.09
    UNE
    -0.09
    ÑĨенÑĤÑĢ
    -0.09
    POSITIVE LOGITS
     enough
    0.12
     fewer
    0.10
    ä»ĸå¦Ī
    0.10
    太å¤ļçļĦ
    0.09
    åİ¿éķ¿
    0.09
    åIJ¬å¾Ĺ
    0.09
    è¶³å¤ŁçļĦ
    0.09
    å±Ģéķ¿
    0.09
    ist
    0.09
    ä¹ĭ声
    0.09
    Activations Density 0.151%

    No Known Activations