© 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. 35914
    Prev
    Next
    INDEX
    Explanations

    indefinite, obscuring, immoral

    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
    æĥ¬
    -0.10
    KIT
    -0.10
    ä¼Ļ
    -0.09
    tek
    -0.09
    èle
    -0.08
    aceous
    -0.08
    inne
    -0.08
    åĬ²
    -0.08
    ооÑĢ
    -0.08
    adol
    -0.08
    POSITIVE LOGITS
    uous
    0.11
    管çIJĨæĿ¡ä¾ĭ
    0.09
    åħ¶å®ŀ
    0.09
    åĢĴæĺ¯
    0.09
    ãĥªãĥ¼
    0.08
     Raider
    0.08
    åıī
    0.08
    atory
    0.08
    顽强
    0.08
    åĪ³
    0.08
    Activations Density 0.002%

    No Known Activations