© 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. 53264
    Prev
    Next
    INDEX
    Explanations

    body, back, top, seat

    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
    æĹ©åľ¨
    -0.08
    uxe
    -0.08
    çī¹åĪ«
    -0.08
     press
    -0.08
    ãĤ·ãĥ¼
    -0.08
     Press
    -0.08
    赶
    -0.08
    press
    -0.07
    quet
    -0.07
     presses
    -0.07
    POSITIVE LOGITS
    åİŁæľī
    0.11
    èĥĥåı£
    0.10
    æ·Ģ
    0.10
    missive
    0.09
    eness
    0.09
    ippy
    0.08
    åĩºç¤º
    0.08
    æ¼ĵ
    0.08
    side
    0.08
    idel
    0.08
    Activations Density 0.511%

    No Known Activations