© 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. 27969
    Prev
    Next
    INDEX
    Explanations

    state abbreviations followed by a period

    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
    åĩ³
    -0.09
    缮æłĩä»»åĬ¡
    -0.09
    çĻŀ
    -0.09
    ITES
    -0.09
    æµ·åĨħå¤ĸ
    -0.09
    èĩªçĦ¶èĢĮ
    -0.08
    åºıå¹ķ
    -0.08
    礼æĭľ
    -0.08
    ails
    -0.08
    CKER
    -0.08
    POSITIVE LOGITS
    æĦļ
    0.09
    elin
    0.08
    enses
    0.08
    æĪijåıĪ
    0.08
    nik
    0.08
    æĺ¯æĪijçļĦ
    0.08
    loe
    0.08
    inois
    0.08
    èĺħ
    0.08
    åĢ¦
    0.08
    Activations Density 0.036%

    No Known Activations