© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8714
    Prev
    Next
    INDEX
    Explanations

    dip compounds

    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
    iling
    -0.10
    ised
    -0.09
    liness
    -0.09
    иÑĩеÑģки
    -0.09
    æĺ¯éĿŀ
    -0.09
    picker
    -0.08
    讵
    -0.08
    ãģªãģĬ
    -0.08
    heid
    -0.08
    aight
    -0.08
    POSITIVE LOGITS
    pery
    0.11
    OrCreate
    0.10
    rupt
    0.10
    ter
    0.09
    обÑĢаз
    0.09
    èĩªå¦Ĥ
    0.09
    çĽİ
    0.09
    룬
    0.09
    ersions
    0.09
    à¸Ľà¸£à¸°
    0.09
    Activations Density 0.009%

    No Known Activations