© 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. 51091
    Prev
    Next
    INDEX
    Explanations

    depend on / rely on

    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
    zel
    -0.09
    åĢĺ
    -0.09
    dek
    -0.08
    æĴŀ
    -0.08
    åĽ½æĥħ
    -0.08
    ä»Ģä¹Īåij¢
    -0.08
    åijĹ
    -0.08
    è°ģçŁ¥éģĵ
    -0.08
    æŧ
    -0.08
     Meredith
    -0.08
    POSITIVE LOGITS
    ably
    0.10
    éļIJ约
    0.09
    pie
    0.09
    ç»Ĩå¾®
    0.08
    pect
    0.08
    pared
    0.08
    thes
    0.08
    èĽ¸
    0.08
     Prescott
    0.08
    nowled
    0.08
    Activations Density 0.011%

    No Known Activations