© 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. 36790
    Prev
    Next
    INDEX
    Explanations

    last names Schmidt, Schneider

    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
    å§Ķä¼ļ
    -0.10
    onders
    -0.09
    unde
    -0.08
    eri
    -0.08
    俸
    -0.08
    ally
    -0.08
    ĺ
    -0.08
    ENTE
    -0.08
    羣æŃ£åģļåĪ°
    -0.08
    å¤
    -0.08
    POSITIVE LOGITS
    stakes
    0.11
    tures
    0.11
    enance
    0.10
    ارÙĬ
    0.10
    èģĶåIJĪä¼ļ
    0.09
    LineColor
    0.09
    è¦ģæĥ³
    0.09
    ãģĹãģ¾ãģĨ
    0.09
    ronic
    0.09
    toolbox
    0.09
    Activations Density 0.007%

    No Known Activations