© 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. 49448
    Prev
    Next
    INDEX
    Explanations

    changing or needing to change

    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
    åĩĮ
    -0.09
    æ³±
    -0.09
    å½ķ
    -0.09
    è¦ģçŁ¥éģĵ
    -0.08
     cours
    -0.08
    iped
    -0.08
     whit
    -0.07
    mel
    -0.07
    ichtet
    -0.07
    som
    -0.07
    POSITIVE LOGITS
    åĽºçĦ¶
    0.21
    ä¸įä¸Ģå®ļ
    0.17
    ä½Ĩè¿Ļ
    0.16
    并ä¸į代表
    0.16
    ä½Ĩå®ĥ
    0.15
    并ä¸įæĺ¯
    0.15
    æľªå¿ħ
    0.14
    ä½Ĩæĺ¯æĪij
    0.14
    ä½ĨæĪij
    0.14
    ä½ĨæĪij们
    0.14
    Activations Density 0.679%

    No Known Activations