© 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. 1133
    Prev
    Next
    INDEX
    Explanations

    situations circumstances conditions

    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
    ä¸įä»ħèĥ½
    -0.09
     popular
    -0.08
    å°ıçĻ½
    -0.08
    åį¯
    -0.08
    çļĦåį±å®³
    -0.08
    adera
    -0.08
    ÑĥлÑĮ
    -0.07
     Contin
    -0.07
    Fact
    -0.07
     Russ
    -0.07
    POSITIVE LOGITS
     situations
    0.16
    ä»Ģä¹ĪæŶåĢĻ
    0.14
     circumstances
    0.13
    è¿Ļ个æŶåĢĻ
    0.12
    æĥħåĨµ
    0.12
    çļĦæĥħåĨµ
    0.12
    åľºåIJĪ
    0.12
    çļĦæĥħå½¢
    0.12
    çŃīæĥħåĨµ
    0.12
    çī¹æ®ĬæĥħåĨµ
    0.12
    Activations Density 0.190%

    No Known Activations