© 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. 17578
    Prev
    Next
    INDEX
    Explanations

    uncorrected and subject to revision

    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
    åħ«å¤§
    -0.10
    æŀ¨
    -0.09
    ä¸ĥ大
    -0.09
    åł¤
    -0.09
    LinkId
    -0.09
    饥饿
    -0.08
    注æĺİ
    -0.08
    erior
    -0.08
    糧
    -0.08
    elpers
    -0.08
    POSITIVE LOGITS
    åı¯èĥ½åĩºçİ°
    0.11
    åı¯èĥ½åŃĺåľ¨
    0.10
    æķ£
    0.09
    åĬ²
    0.09
    æľªç»ı
    0.09
    éħį
    0.08
    _ONCE
    0.08
    级åĪ«çļĦ
    0.08
    conc
    0.08
     rigor
    0.08
    Activations Density 0.094%

    No Known Activations