© 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. 53369
    Prev
    Next
    INDEX
    Explanations

    http://

    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
    anter
    -0.09
     кÑĥд
    -0.08
    ä¼łæī¿
    -0.08
    äºij
    -0.08
    æ®Ĭ
    -0.08
    دار
    -0.08
    icker
    -0.08
     Sind
    -0.08
    åĽłæŀľ
    -0.08
    éĢļ讯åijĺ
    -0.08
    POSITIVE LOGITS
    æ¶ĪçģŃ
    0.09
     Lah
    0.09
    atsu
    0.09
    æĸĽ
    0.08
    æķijåij½
    0.08
    èŀĥèŁ¹
    0.08
    xDD
    0.08
    ned
    0.08
    ä¸ºçĽ®æłĩ
    0.08
    cean
    0.08
    Activations Density 0.160%

    No Known Activations