© 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. 48255
    Prev
    Next
    INDEX
    Explanations

    permitted provided

    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
    ym
    -0.09
    æĢİä¹Īèĥ½
    -0.09
    åħ¶å®ĥéĹ®é¢ĺ
    -0.08
    è¦ģä¹Ī
    -0.08
    éķ¿æķĪ
    -0.08
    YM
    -0.08
    æł¹æľ¬æ²¡æľī
    -0.08
     Ñıв
    -0.08
    è¿Ļ次
    -0.08
    alion
    -0.08
    POSITIVE LOGITS
    åıªè¦ģ
    0.24
    åıªè¦ģæĺ¯
    0.20
    åıªè¦ģä½ł
    0.15
    ãģŁãģłãģĹ
    0.15
    ä½Ĩ
    0.15
    åīįæıIJæĺ¯
    0.15
    åıªè¦ģæľī
    0.15
    ä½Ĩæĺ¯
    0.15
    ä¸Ģå®ļç¨ĭ度
    0.13
    ä½Ĩæĺ¯å¦Ĥæŀľ
    0.13
    Activations Density 0.164%

    No Known Activations