© 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. 20407
    Prev
    Next
    INDEX
    Explanations

    issues like

    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
    MUX
    -0.12
    使æĪij
    -0.09
    å¿ĥ缮
    -0.09
    assis
    -0.09
    èĺħ
    -0.09
    åĬ¿
    -0.09
    .dao
    -0.09
    鸢
    -0.08
     Arb
    -0.08
     Georgetown
    -0.08
    POSITIVE LOGITS
    æľīå¤ļä¹Ī
    0.10
    ç»Ī究
    0.09
     imm
    0.08
     zo
    0.08
    åµ´
    0.08
    noinspection
    0.08
    æµ·éĩı
    0.08
    5
    0.08
    4
    0.08
    æݢ访
    0.08
    Activations Density 3.851%

    No Known Activations