© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50850
    Prev
    Next
    INDEX
    Explanations

    hydrogen bonding and extraction

    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
     intervening
    -0.09
    culate
    -0.09
    ahun
    -0.09
    èĬĤæĹ¥
    -0.09
    tery
    -0.09
    ily
    -0.09
    åĮĸå¦Ĩ
    -0.09
    itative
    -0.09
    iful
    -0.08
    lico
    -0.08
    POSITIVE LOGITS
    .Features
    0.09
    åIJĮå¿Ĺ们
    0.09
    å®ĩå®Ļ
    0.09
    ppo
    0.09
    樽
    0.09
    emies
    0.09
    èĩªè±ª
    0.08
    å»Ł
    0.08
    殿ä¸ĭ
    0.08
     lẽ
    0.08
    Activations Density 0.136%

    No Known Activations