© 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. 21450
    Prev
    Next
    INDEX
    Explanations

    rules that, manages to, perfect thing

    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
    伫
    -0.12
    æĺĨä»ij
    -0.11
    æĹłæķĮ
    -0.11
    æķ²
    -0.10
    俱ä¹IJ
    -0.09
    æģĥ
    -0.09
    à¹Ģà¸ĸ
    -0.09
    çī¹æ®Ĭ
    -0.09
    ä¸į失
    -0.09
    Sir
    -0.09
    POSITIVE LOGITS
    ä¸į符åIJĪ
    0.10
    讲究
    0.10
    详
    0.09
    éģµå®Ī
    0.09
     flawless
    0.09
    æłĩåĩĨåĮĸ
    0.09
    è¦ģæ±Ĥ
    0.09
     Eh
    0.09
    å®Įç¾İ
    0.09
    çIJĨæĥ³
    0.08
    Activations Density 0.104%

    No Known Activations