© 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. 27102
    Prev
    Next
    INDEX
    Explanations

    to buy or pay

    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
    åģļå¾Ĺ
    -0.12
    å§ij
    -0.10
    寧
    -0.09
    éļ¾ä»¥
    -0.08
    顺åĪ©
    -0.08
    æĭĴä¸į
    -0.08
    æĸ¹ä¾¿
    -0.08
    (guid
    -0.08
    Shortcut
    -0.08
    Unauthorized
    -0.08
    POSITIVE LOGITS
    æŁ¥çľĭåħ¨æĸĩ
    0.10
    æīįèĥ½å¤Ł
    0.09
    åĩłæŃ¥
    0.09
    è¿Ļæł·æīįèĥ½
    0.09
    ä¹Łåıªæľī
    0.09
    ãģĮãģĤ
    0.08
    çī¹åĪ«å£°æĺİ
    0.08
    æīįèĥ½
    0.08
    ä¹Łåıªèĥ½
    0.08
    ä¸įå°ıçļĦ
    0.08
    Activations Density 0.094%

    No Known Activations