© 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. 58242
    Prev
    Next
    INDEX
    Explanations

    warship types and names

    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
    æĿĪ
    -0.09
    anson
    -0.09
    adian
    -0.09
    cci
    -0.09
    å¤Ħå¢ĥ
    -0.09
    æģŃæķ¬
    -0.08
    èħ¥
    -0.08
     Martian
    -0.08
     Kab
    -0.08
    Injected
    -0.08
    POSITIVE LOGITS
    ä¸Ģèīĺ
    0.10
    èĪ°
    0.09
    èĪ¹åıª
    0.09
    igua
    0.09
    黼
    0.09
     водо
    0.09
    _DP
    0.09
    -peer
    0.08
    ROC
    0.08
    older
    0.08
    Activations Density 0.119%

    No Known Activations