© 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. 56515
    Prev
    Next
    INDEX
    Explanations

    optimization and search methods

    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
    endir
    -0.11
    æĹ¶ç©º
    -0.09
    éļIJå½¢
    -0.09
    å·´æĭī
    -0.09
    ç²²
    -0.09
    åĪĩãĤĬ
    -0.09
    ITICAL
    -0.09
     khúc
    -0.08
    å®Įæķ´æĢ§
    -0.08
    èĬŃ
    -0.08
    POSITIVE LOGITS
    ä¸Ģ代
    0.09
    apy
    0.09
    äºļè¿IJä¼ļ
    0.09
    ä¿ĥ
    0.09
    SearchParams
    0.09
    orks
    0.08
    WithError
    0.08
    æIJľç´¢
    0.08
     Hole
    0.08
    adam
    0.08
    Activations Density 0.107%

    No Known Activations