© 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. 35590
    Prev
    Next
    INDEX
    Explanations

    land use

    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
    éĻ·
    -0.09
    æ°ĶåĬ¿
    -0.09
    绡
    -0.09
    æĹ·
    -0.09
    folios
    -0.08
    hoff
    -0.08
    足以
    -0.08
    à¸ĩาม
    -0.08
    æĻºèĥ½å®¶å±ħ
    -0.08
    ç°Ł
    -0.08
    POSITIVE LOGITS
    ÑģÑı
    0.10
    ust
    0.09
    å¤ļåħĥåĮĸ
    0.09
    æµ®åĬ¨
    0.08
    涤
    0.08
    zero
    0.08
    interp
    0.08
    念
    0.08
    ä½İä¸ĭ
    0.08
    undi
    0.08
    Activations Density 0.005%

    No Known Activations