© 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. 27595
    Prev
    Next
    INDEX
    Explanations

    blocking, blockade, cordons, Barracks

    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
    lings
    -0.09
    èī¯å¥½
    -0.09
    ä½ĵè´¨
    -0.08
    åķĦ
    -0.08
    uzzi
    -0.08
     Nuggets
    -0.08
    宣å¸ĥ
    -0.08
    elijke
    -0.08
    å¥ij
    -0.08
    åľĴ
    -0.08
    POSITIVE LOGITS
     chắn
    0.12
    ä½ıäºĨ
    0.12
    æĭ¦
    0.11
    å¾Ĺä½ı
    0.10
    åĿĿ
    0.10
    åłµ
    0.10
    çĪ±å¿ĥ
    0.09
    ми
    0.09
     Ñģобой
    0.09
    ades
    0.09
    Activations Density 0.013%

    No Known Activations