© 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. 54788
    Prev
    Next
    INDEX
    Explanations

    science and researchers

    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
     Goldberg
    -0.08
     wear
    -0.08
    CHANNEL
    -0.08
    é»Ħéĩij
    -0.08
    æ¯Ľ
    -0.08
    碾
    -0.08
     cin
    -0.07
    _STAR
    -0.07
    æĪ·
    -0.07
    illi
    -0.07
    POSITIVE LOGITS
    åľ°çIJĥ
    0.16
    Earth
    0.13
     Earth
    0.12
    åľ°è´¨
    0.11
    仪åĻ¨
    0.10
    为空
    0.10
    .qq
    0.10
     mantle
    0.10
    å²©çŁ³
    0.09
    æ°´éĩı
    0.09
    Activations Density 0.111%

    No Known Activations