© 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. 33163
    Prev
    Next
    INDEX
    Explanations

    parenthetical phrases or clauses

    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
     mastur
    -0.10
    åĸīåĴĻ
    -0.09
    å¿ĸ
    -0.09
     optarg
    -0.09
     Grave
    -0.09
    幺
    -0.09
    .createTextNode
    -0.09
    ABCDEFGHI
    -0.09
    PTY
    -0.09
    æŀ¶åŃIJ
    -0.09
    POSITIVE LOGITS
    楼主
    0.08
    bai
    0.08
    .JPG
    0.08
    é¢ĺ主
    0.07
    ï¾ĭ
    0.07
     "
    0.07
    åŃĹ第
    0.07
    0.07
     '
    0.06
    sic
    0.06
    Activations Density 1.244%

    No Known Activations