© 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. 7223
    Prev
    Next
    INDEX
    Explanations

    tattoo and ink

    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
    -facing
    -0.10
    寺
    -0.09
    åĬ²
    -0.09
     اÙĦدÙĨÙĬا
    -0.09
    idget
    -0.09
    éĩijéĵ¶
    -0.09
    venir
    -0.09
    å®ļä½į
    -0.09
    åħħè£ķ
    -0.08
     Ãľnivers
    -0.08
    POSITIVE LOGITS
    缯
    0.08
    èĻ¬
    0.08
    lias
    0.08
    lip
    0.08
    åIJĽ
    0.08
    é©»
    0.08
    å°ıå°ı
    0.08
    ables
    0.08
    el
    0.07
    å°ıå°ıçļĦ
    0.07
    Activations Density 0.007%

    No Known Activations