© 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. 21521
    Prev
    Next
    INDEX
    Explanations

    proper nouns including names and places

    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
    -0.13
    æ¯ĵ
    -0.09
    è¿ĻåĦ¿
    -0.09
    äºĽä»Ģä¹Ī
    -0.09
    èĬĬ
    -0.08
    usercontent
    -0.08
    è¿Ļä¹Ī说
    -0.08
    ätt
    -0.08
    Eta
    -0.08
    èĬ¸
    -0.08
    POSITIVE LOGITS
    sWith
    0.14
    åŃIJéĩĮ
    0.11
    cia
    0.09
    yla
    0.09
    etros
    0.09
    èº
    0.09
    sert
    0.09
    ement
    0.08
    åĦ¿
    0.08
    ãĥ¡ãĥ³ãĥĪ
    0.08
    Activations Density 0.047%

    No Known Activations