© 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. 26474
    Prev
    Next
    INDEX
    Explanations

    bra or bra in compounds

    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
    çĦ¶æĺ¯
    -0.13
    lic
    -0.10
    çĦ¶
    -0.09
    ammen
    -0.09
    ni
    -0.09
    naire
    -0.09
    áŁĴáŀ
    -0.09
    æ´²
    -0.09
    nu
    -0.09
    اش
    -0.09
    POSITIVE LOGITS
    å©¿
    0.11
    imps
    0.10
    istic
    0.10
    äºĨä¸Ģç³»åĪĹ
    0.10
    isks
    0.09
    èĩĥ
    0.09
    èıĶ
    0.09
    ä¸ĢéĹª
    0.09
    aming
    0.09
    vez
    0.09
    Activations Density 0.037%

    No Known Activations