© 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. 20163
    Prev
    Next
    INDEX
    Explanations

    names ending in "ley" or "ana" or "zen"

    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
    boro
    -0.10
    urs
    -0.10
    夺
    -0.10
    urses
    -0.09
    ville
    -0.09
    idal
    -0.09
    esis
    -0.08
    bil
    -0.08
    rap
    -0.08
    éĢ¼è¿ij
    -0.08
    POSITIVE LOGITS
    -spe
    0.10
    漫æŃ¥
    0.10
    exion
    0.09
    åĬ¨åĬĽ
    0.09
    èĬĭ
    0.09
    ç«ĭãģ¡
    0.09
    æĭ£
    0.09
    tern
    0.09
    ç»ķ
    0.08
    çĥŁåĽ±
    0.08
    Activations Density 0.003%

    No Known Activations