© 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. 30780
    Prev
    Next
    INDEX
    Explanations

    maritime, nautical, boat, ship

    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
    çĸ£
    -0.09
    tep
    -0.09
    çIJ¨
    -0.09
    æĥ®
    -0.09
     vig
    -0.09
    aurus
    -0.09
    pora
    -0.09
     Legion
    -0.09
    æĭĬ
    -0.09
    pres
    -0.09
    POSITIVE LOGITS
    èĪ¹
    0.17
    ä¸Ģèīĺ
    0.16
    èĪ¹åıª
    0.15
    èĪªè¡Į
    0.14
    èĪŁ
    0.14
    èīĺ
    0.13
    èĪ¹ä¸Ĭ
    0.13
    èĪªæµ·
    0.12
    èĪ°
    0.12
    éĤ®è½®
    0.12
    Activations Density 0.104%

    No Known Activations