© 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. 51388
    Prev
    Next
    INDEX
    Explanations

    click 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
    ORN
    -0.10
    ä¸Ģå¼Ģå§ĭå°±
    -0.09
    ç³Ł
    -0.09
    URN
    -0.09
    æĢİä¹Īåģļ
    -0.09
    æĢİä¹ĪåĽŀäºĭ
    -0.09
    åħįè´£
    -0.08
    è¿Ħ
    -0.08
    ĪæĿĥ
    -0.08
    .clients
    -0.08
    POSITIVE LOGITS
    éĹ³
    0.09
    룬
    0.09
    çĭŃ
    0.08
    形象
    0.08
    åį¯
    0.08
    æĬ±
    0.08
    logo
    0.08
    hazi
    0.08
    æŁĦ
    0.08
    alam
    0.07
    Activations Density 0.005%

    No Known Activations