© 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. 33164
    Prev
    Next
    INDEX
    Explanations

    Dom and related words

    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
    orde
    -0.10
    .nlm
    -0.09
    trl
    -0.09
    æ¼ķ
    -0.09
    ÑĢон
    -0.09
    isel
    -0.09
    è¾ĥéĩı
    -0.08
    pNet
    -0.08
    è·ijéģĵ
    -0.08
    麻çĹ¹
    -0.08
    POSITIVE LOGITS
    estic
    0.16
     Ñģобой
    0.11
    utton
    0.11
    ingu
    0.10
    ains
    0.10
    ä¸Ģ次次
    0.10
    å¥Ń
    0.09
     ë¶Ī구íķĺê³ł
    0.09
    AINS
    0.09
    stration
    0.09
    Activations Density 0.039%

    No Known Activations