© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20326
    Prev
    Next
    INDEX
    Explanations

    Company abbreviations

    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
    /or
    -0.14
    ened
    -0.11
    å°¼äºļ
    -0.09
    etheless
    -0.08
    ustral
    -0.08
    tas
    -0.08
    çĤ¹å¤ļ
    -0.08
    ä¼Ĭå§ĭ
    -0.08
    æĹ¥æĬ¥ç¤¾
    -0.08
    å®ŀçī©
    -0.08
    POSITIVE LOGITS
    ftware
    0.15
    zelf
    0.14
    IGINAL
    0.12
    iversal
    0.12
    ׾
    0.12
    autiful
    0.12
    ufact
    0.10
    åľ¨åIJĮä¸Ģ
    0.10
    çļĦéĤ£ä¸Ģ
    0.09
    ãĥ£
    0.09
    Activations Density 0.148%

    No Known Activations