© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8066
    Prev
    Next
    INDEX
    Explanations

    Created by or on

    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
    çĴŀ
    -0.09
    åľ¨äº¬
    -0.08
    裹
    -0.08
    éĺ¶çº§
    -0.08
     flock
    -0.08
    åľ¨æĪijçļĦ
    -0.08
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.08
    åı²
    -0.07
    /pol
    -0.07
    æ·ij
    -0.07
    POSITIVE LOGITS
    ëī´ìĬ¤
    0.10
    _COMPILE
    0.10
    mát
    0.09
    æ¨Ł
    0.09
    odore
    0.09
    adh
    0.09
    makt
    0.09
     Dro
    0.09
    _tolerance
    0.08
    å©¿
    0.08
    Activations Density 0.029%

    No Known Activations