© 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. 4802
    Prev
    Next
    INDEX
    Explanations

    Chan Zuckerberg

    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
    imb
    -0.09
    çĵ®
    -0.09
    neath
    -0.09
    pta
    -0.09
    æ±Ĭ
    -0.08
    aus
    -0.08
    æĭĽåķĨ
    -0.08
    æĸ°æĶ¿
    -0.08
    岸
    -0.08
    è¡·
    -0.08
    POSITIVE LOGITS
    alysis
    0.11
    tering
    0.11
    tered
    0.10
    åĤ¥
    0.09
    ../
    0.09
    @qq
    0.09
    ÙĪØ®
    0.09
    夫
    0.09
    annel
    0.09
     бÑĥдÑĥ
    0.09
    Activations Density 0.005%

    No Known Activations