© 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. 5147
    Prev
    Next
    INDEX
    Explanations

    durations of media or events

    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
    è°Īèµ·
    -0.10
    ä»ĸèĩªå·±
    -0.10
    å°ijè§ģ
    -0.09
    _singular
    -0.09
    éta
    -0.09
     dru
    -0.09
    ETA
    -0.09
    åĵģç§į
    -0.09
    Iterations
    -0.09
    èĺijèıĩ
    -0.08
    POSITIVE LOGITS
    åĭŁéĽĨ
    0.09
    çĥ§
    0.08
     ACK
    0.08
    oll
    0.08
     Cath
    0.08
    åĭŁ
    0.08
    ä¿ĥ
    0.08
    loads
    0.08
    姻
    0.08
    ä¸įæĸŃå®ĮåĸĦ
    0.07
    Activations Density 0.020%

    No Known Activations