© 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. 17973
    Prev
    Next
    INDEX
    Explanations

    names of people and places

    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
    æĥĨ
    -0.11
    urd
    -0.10
    å»Ĭ
    -0.09
    èij«èĬ¦
    -0.09
    å¾®ç¬ij
    -0.09
    温åĴĮ
    -0.08
     dilig
    -0.08
    åĴĮåıijå±ķ
    -0.08
    _mime
    -0.08
     Cosby
    -0.08
    POSITIVE LOGITS
    ä»»æĢ§
    0.10
    主æĦı
    0.10
    壮è§Ĥ
    0.10
    宸
    0.10
    åİĮ
    0.10
    龸éģĵ
    0.10
    éªĦåĤ²
    0.09
    强硬
    0.09
    强çĥĪ
    0.09
    强åĬ¿
    0.09
    Activations Density 0.158%

    No Known Activations