© 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. 54062
    Prev
    Next
    INDEX
    Explanations

    .gov or Gov followed by t . or Con

    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
    稿
    -0.09
    ifying
    -0.08
    ../../../
    -0.08
    tors
    -0.08
    åĴİ
    -0.08
    igm
    -0.08
    omatic
    -0.08
    éĿŀ常æĺİæĺ¾
    -0.08
    åķĨæĬ¥
    -0.08
    orbit
    -0.08
    POSITIVE LOGITS
    enance
    0.10
    ì§ģ
    0.09
    atl
    0.09
    rig
    0.09
    annis
    0.09
    è¡Ļ
    0.09
    theast
    0.09
    ðŁı»
    0.09
    å±ĤéĿ¢
    0.09
    ëĭĪëĭ¤
    0.08
    Activations Density 0.009%

    No Known Activations