© 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. 5690
    Prev
    Next
    INDEX
    Explanations

    each item/unit

    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
    .qt
    -0.09
    endi
    -0.09
    -spinner
    -0.09
    éĤ£åĦ¿
    -0.09
    .Designer
    -0.09
    éĥľ
    -0.09
    è®®äºĭ
    -0.09
    (OP
    -0.08
    ä¸ĩ家
    -0.08
    ä¸įæŃ¢
    -0.08
    POSITIVE LOGITS
     individual
    0.10
    alysis
    0.10
    æī¹æ¬¡
    0.10
     Individual
    0.10
     individ
    0.09
    妥åĸĦ
    0.09
    æ¯ıä¸Ģ
    0.09
    个ä½ĵ
    0.09
    nels
    0.09
    åĩ¡æĺ¯
    0.09
    Activations Density 0.085%

    No Known Activations