© 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. 2521
    Prev
    Next
    INDEX
    Explanations

    Stevens and similar names

    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
    Ñĥк
    -0.11
    abouts
    -0.09
    noc
    -0.09
    itionally
    -0.09
    trib
    -0.09
    æİ°
    -0.09
    è¶Ķ
    -0.08
    \<^
    -0.08
    ya
    -0.08
    athon
    -0.08
    POSITIVE LOGITS
    hood
    0.10
    ниÑĨ
    0.09
    inheritDoc
    0.09
     Verb
    0.09
    æĺ¯ä¸Ģ件
    0.09
    ize
    0.08
    è²Į
    0.08
    ìĤ¬íķŃ
    0.08
    Creators
    0.08
    est
    0.08
    Activations Density 0.004%

    No Known Activations