© 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. 11481
    Prev
    Next
    INDEX
    Explanations

    government and security information

    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
    æķij
    -0.10
    鼨
    -0.09
    rompt
    -0.09
    åī¥
    -0.09
     surv
    -0.09
    Çģ
    -0.08
    ç»ĥ
    -0.08
    -fw
    -0.08
     Cyr
    -0.08
    æľīåIJį
    -0.08
    POSITIVE LOGITS
    ä¿Ŀå¯Ĩ
    0.12
    æķıæĦŁ
    0.11
    åĽ½å®ī
    0.10
     clearance
    0.10
    æ³Ħéľ²
    0.10
    讪
    0.09
    æIJ¬è¿IJ
    0.09
     Clearance
    0.09
    æIJ¬åĪ°
    0.09
    æĭŁ
    0.09
    Activations Density 0.064%

    No Known Activations