© 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. 5291
    Prev
    Next
    INDEX
    Explanations

    organic light-emitting diodes

    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
    享
    -0.11
    avra
    -0.10
    å®ľå±ħ
    -0.09
    饷
    -0.09
    æ´
    -0.09
    åĽŀå½Ĵ
    -0.09
    å¼ĢåĪĽ
    -0.08
    俶
    -0.08
     Cous
    -0.08
    quel
    -0.08
    POSITIVE LOGITS
     Recon
    0.10
    arshal
    0.10
    å²Ľ
    0.09
    骨干
    0.09
    idf
    0.09
    æ¦ľ
    0.09
    æ¶Ĥ
    0.09
    elin
    0.09
     HOLDERS
    0.09
    ulla
    0.09
    Activations Density 0.304%

    No Known Activations