© 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. 17350
    Prev
    Next
    INDEX
    Explanations

    airport screening, prosthetics

    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
    æĬĬèĩªå·±
    -0.10
    è·
    -0.10
    WARE
    -0.10
    èĪį
    -0.09
    _SOCKET
    -0.09
    è¡°
    -0.09
    _AUT
    -0.09
    æ°¨
    -0.09
    ä¿Ŀ
    -0.08
    æ¡Ĩ
    -0.08
    POSITIVE LOGITS
    å®īæ£Ģ
    0.12
    毳
    0.10
    çĸij
    0.10
     airport
    0.09
    ç§ĭåĨ¬
    0.09
    æĹħéĢĶ
    0.09
    æĹħ
    0.09
    æĨ¬
    0.09
    åı¯çĸij
    0.08
     Airport
    0.08
    Activations Density 0.076%

    No Known Activations