© 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. 52826
    Prev
    Next
    INDEX
    Explanations

    intended for educational, research, or entertainment purposes

    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
    ·»
    -0.09
    æļ´é£İ
    -0.09
    çħ¦
    -0.09
    stance
    -0.09
    é»Ħæĺı
    -0.08
    Ãłn
    -0.08
    axed
    -0.08
    ateral
    -0.08
    erial
    -0.08
    è§Ĩå¯Ł
    -0.08
    POSITIVE LOGITS
    åīľ
    0.10
    ots
    0.08
    åįģä¸ĩ
    0.08
    æľīåIJį
    0.08
    åIJį
    0.08
    æ°ij主åħļ
    0.08
    /sbin
    0.08
    äºĶçĻ¾
    0.08
    /widget
    0.08
    è·Į
    0.08
    Activations Density 0.004%

    No Known Activations