© 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. 26802
    Prev
    Next
    INDEX
    Explanations

    adults

    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
    rist
    -0.12
    é£İåIJ¹
    -0.10
    åįĵ
    -0.10
    ä½łèĩªå·±
    -0.10
    æ´¾
    -0.10
    riere
    -0.10
    å¯Įæ°ij
    -0.10
    åĬ¨äºº
    -0.10
    eros
    -0.10
    лÑij
    -0.10
    POSITIVE LOGITS
    ´
    0.10
    çĵ®
    0.08
    uration
    0.08
    å°¤åħ¶æĺ¯
    0.08
    عر
    0.08
    åĢij
    0.08
    menus
    0.08
    ðŁı»
    0.08
    baum
    0.08
    izr
    0.08
    Activations Density 0.016%

    No Known Activations