© 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. 11674
    Prev
    Next
    INDEX
    Explanations

    objects stacking and balancing

    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
    çģ¿
    -0.09
    ãĥıãĤ¦ãĤ¹
    -0.08
    缧
    -0.08
    èļķ
    -0.08
    æ²ĥå°Ķ
    -0.08
    çķ´
    -0.08
    è¢Ħ
    -0.08
    ç¾²
    -0.08
    å¸ĥæĭī
    -0.08
    çķĶ
    -0.08
    POSITIVE LOGITS
    æIJ¬è¿IJ
    0.15
    é©®
    0.14
    åłĨæĶ¾
    0.14
    ä½ĵéĩį
    0.13
    çī©åĵģ
    0.13
    ç¨³åĽº
    0.12
    éĩįéĩı
    0.12
    ä¸į稳å®ļ
    0.12
     unstable
    0.12
    éĩįå¿ĥ
    0.12
    Activations Density 0.129%

    No Known Activations