© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52801
    Prev
    Next
    INDEX
    Explanations

    in followed by a location

    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
    æīĢå±ŀ
    -0.10
    罪
    -0.10
    åľ¨åĮĹ京
    -0.10
    ä¸ĢæĬ¹
    -0.09
    åľ¨å½ĵåľ°
    -0.09
    褶
    -0.09
    ç¾İèģĶ
    -0.09
    åŁ¹è®ŃæľºæŀĦ
    -0.09
    麽
    -0.08
    æĪį
    -0.08
    POSITIVE LOGITS
    åįĥéĩĮ
    0.09
     пен
    0.08
    é¹ij
    0.08
    undy
    0.08
    åħĪåIJİ
    0.08
    å°ı康
    0.08
    InnerHTML
    0.08
     ÑĢанее
    0.08
    çĶŁæ¶¯
    0.07
    涯
    0.07
    Activations Density 0.090%

    No Known Activations