© 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. 53159
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    åĬŁå¤«
    -0.09
    æŃ¤åŁºç¡Ģä¸Ĭ
    -0.09
    ween
    -0.08
    ide
    -0.08
    çIJĨ
    -0.08
    ay
    -0.07
    åĩī
    -0.07
    åįĬå°ıæŶ
    -0.07
    å¤ķ
    -0.07
     Sons
    -0.07
    POSITIVE LOGITS
    [email
    0.12
    ä¿¡ç®±
    0.11
    kir
    0.10
    ople
    0.09
    ç»ĺ
    0.09
    çĹ
    0.08
    è·³åĩº
    0.08
    (email
    0.08
    tsy
    0.08
    ippo
    0.08
    Activations Density 0.000%

    No Known Activations