© 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. 11133
    Prev
    Next
    INDEX
    Explanations

    CPU, RAM, resources

    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
    Ñģид
    -0.10
    åĺ¹
    -0.10
    æĻŀ
    -0.10
    åįļè§Ī
    -0.10
    延ç»Ń
    -0.09
    éĵ¿
    -0.09
    æIJĢ
    -0.09
    åĭĩæķ¢
    -0.09
    çĤī
    -0.09
    uant
    -0.08
    POSITIVE LOGITS
    cpu
    0.12
     CPU
    0.11
     cpu
    0.11
    CPU
    0.11
    è¿IJè¡Į
    0.10
    æĢ§èĥ½
    0.10
    è¿IJç®Ĺ
    0.10
     performance
    0.10
     ram
    0.09
     strapped
    0.09
    Activations Density 0.134%

    No Known Activations