© 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. 53993
    Prev
    Next
    INDEX
    Explanations

    reviewing information

    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
    ows
    -0.09
    对æѤ
    -0.09
    æĭĦ
    -0.09
    è¦ģåѦä¼ļ
    -0.09
    岬
    -0.08
    odi
    -0.08
    管çIJĨä¸Ńå¿ĥ
    -0.08
    igli
    -0.08
    æł¸ç®Ĺ
    -0.08
    ç½ħ
    -0.08
    POSITIVE LOGITS
    缸åħ³æĶ¿çŃĸ
    0.09
    以å¾Ģ
    0.09
    resher
    0.09
     existing
    0.09
    kj
    0.09
     tuyá»ĥn
    0.09
    è¿ĩåİ»çļĦ
    0.09
    åħĪè¿ĽæĬĢæľ¯
    0.09
    enie
    0.09
    kill
    0.09
    Activations Density 0.039%

    No Known Activations