© 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. 32756
    Prev
    Next
    INDEX
    Explanations

    encoding, GANs, GTX, or file types

    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
    éĤij
    -0.11
    bud
    -0.10
    ç¡IJ
    -0.10
    otas
    -0.10
    kte
    -0.09
    éĺĶ
    -0.09
     bud
    -0.09
    uling
    -0.09
    å¢ħ
    -0.09
    åķ»
    -0.09
    POSITIVE LOGITS
    ä¸įèĥ½åĨį
    0.09
    ä¸ī代
    0.09
    æĿĤå¿Ĺ社
    0.08
    ราว
    0.08
    FAQ
    0.08
    tern
    0.08
     FAG
    0.08
    éĵ¡
    0.08
     canvas
    0.08
    å²ļ
    0.08
    Activations Density 0.022%

    No Known Activations