© 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. 48358
    Prev
    Next
    INDEX
    Explanations

    adults

    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
    .must
    -0.09
    æµ·å²Ľ
    -0.08
    è§Ħç«ł
    -0.08
    èģ¯åIJĪ
    -0.08
    åıªä¸º
    -0.08
    çŃ¹å»º
    -0.08
    èĺĸ
    -0.08
    .capture
    -0.08
    åĩºçĤī
    -0.08
    der
    -0.08
    POSITIVE LOGITS
    æĪIJ年人
    0.26
    æĪIJ人
    0.25
     adult
    0.23
    adult
    0.22
     adults
    0.22
     Adults
    0.22
    Adult
    0.21
    大人
    0.21
     Adult
    0.18
     adultos
    0.18
    Activations Density 0.116%

    No Known Activations