© 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. 55184
    Prev
    Next
    INDEX
    Explanations

    cardboard materials

    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
    ç»ĵçŁ³
    -0.09
    åIJĪæł¼
    -0.09
    åIJįä¹ī
    -0.09
    oven
    -0.09
    è¾¾æłĩ
    -0.08
    åįĩ
    -0.08
    æĮł
    -0.08
    京津
    -0.08
     Qualified
    -0.08
    æĬ±
    -0.08
    POSITIVE LOGITS
    åİļéĩį
    0.10
    enia
    0.10
    åİļ度
    0.10
    纸
    0.09
    ä¹Ķ
    0.09
    åīĮ
    0.08
     Oak
    0.08
    cin
    0.08
    åħ¬å¼Ģåıijè¡Į
    0.08
    榧
    0.08
    Activations Density 0.134%

    No Known Activations