© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20805
    Prev
    Next
    INDEX
    Explanations

    artistic director

    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
    isser
    -0.10
    жÑĥ
    -0.09
    rence
    -0.09
    ings
    -0.09
    иÑĪ
    -0.08
     Ñģобой
    -0.08
    æł¸å¿ĥæĬĢæľ¯
    -0.08
    isy
    -0.08
    TURE
    -0.08
    æĪĸå¤ļ
    -0.08
    POSITIVE LOGITS
    ALLY
    0.11
    ally
    0.10
    uffs
    0.10
    otle
    0.09
    rouw
    0.09
    -minded
    0.09
    -looking
    0.09
     endeavor
    0.09
    åįģ足
    0.09
    çĵ¢
    0.09
    Activations Density 0.003%

    No Known Activations