© 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. 55867
    Prev
    Next
    INDEX
    Explanations

    Latin endings

    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
    åĴ«
    -0.10
    pine
    -0.09
    鼶è·Ŀ离
    -0.09
    razier
    -0.08
    çī¹æľīçļĦ
    -0.08
    æİĸ
    -0.08
    cept
    -0.08
    ceptar
    -0.08
    bjerg
    -0.08
    orous
    -0.07
    POSITIVE LOGITS
    forth
    0.09
     trick
    0.09
    ened
    0.08
    çĸı
    0.08
    éĢīçĶ¨
    0.08
    ä¸Ģ头
    0.08
    busy
    0.08
    icts
    0.08
    icot
    0.08
    çĹķ
    0.08
    Activations Density 0.005%

    No Known Activations