© 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. 34128
    Prev
    Next
    INDEX
    Explanations

    URLs, namespaces, or PHP library components

    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
     bul
    -0.11
    æīª
    -0.08
    azor
    -0.08
    åĪĩ
    -0.08
    è´ª
    -0.08
     val
    -0.07
    åħ±è¯Ĩ
    -0.07
    azar
    -0.07
     prer
    -0.07
     text
    -0.07
    POSITIVE LOGITS
     تصÙĨÙĬÙģ
    0.10
    .byId
    0.10
    å¦Ļ
    0.09
    èĭľ
    0.09
    aversable
    0.09
    ctrine
    0.09
    æį§
    0.09
    PropertyParams
    0.09
    ìľ
    0.09
    åıijå¸ĥçļĦ
    0.09
    Activations Density 0.561%

    No Known Activations