© 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. 21526
    Prev
    Next
    INDEX
    Explanations

    female relationships and life struggles

    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
    æīĵæŀ¶
    -0.10
    çīĪæĿĥæīĢæľī
    -0.09
    .Css
    -0.09
    åIJĥ饱
    -0.09
    frey
    -0.09
    æºħ
    -0.09
     Kemp
    -0.09
    æģ¶åĬ£
    -0.08
    æIJ¬è¿IJ
    -0.08
    iggins
    -0.08
    POSITIVE LOGITS
     Wall
    0.09
    家åºŃ
    0.09
    Multiplicity
    0.08
    æľīä¸ĢçĤ¹
    0.08
    çķ¥
    0.08
    _terminal
    0.08
    åIJĮåŁİ
    0.08
    _BUS
    0.08
     Weekend
    0.07
    eti
    0.07
    Activations Density 0.079%

    No Known Activations