© 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. 10036
    Prev
    Next
    INDEX
    Explanations

    chimpanzees and Kardashians

    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
     Canter
    -0.09
    ating
    -0.09
    åĨ»
    -0.08
    踵
    -0.08
    æ¶Īæŀģ
    -0.08
    laps
    -0.08
    gles
    -0.08
    .mu
    -0.08
    minster
    -0.08
    çݰ象
    -0.08
    POSITIVE LOGITS
    ÙĬÙĬÙĨ
    0.09
    éģķãģĦ
    0.09
    ç½ijè´Ń
    0.08
    æĽĿ
    0.08
    agen
    0.08
     amalg
    0.08
    为æĬĵ
    0.08
    road
    0.08
    读åIJİ
    0.08
    _HDR
    0.08
    Activations Density 0.006%

    No Known Activations