© 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. 35932
    Prev
    Next
    INDEX
    Explanations

    na

    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
    é¤ĺ
    -0.09
    ä¸ĭå·´
    -0.09
    éļIJ
    -0.09
    rag
    -0.09
     вÑĢемени
    -0.09
    çĦ¶æĺ¯
    -0.09
    hus
    -0.09
    é¾Ħ
    -0.08
    sv
    -0.08
    ponent
    -0.08
    POSITIVE LOGITS
    utilus
    0.13
    0.10
    fty
    0.10
    ughty
    0.10
    nda
    0.10
    æ¡Ĩ
    0.09
    asty
    0.09
    æ²£
    0.09
    pec
    0.09
    abox
    0.09
    Activations Density 0.048%

    No Known Activations